© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 32437
    Prev
    Next
    INDEX
    Explanations

    information related to casting spells and their effects, including details about range, animation, activation time, multiple hits, and skill interaction

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    71
    +0.04
    0.5%
    738
    +0.04
    0.5%
    16
    +0.03
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.04
    0.24
    549
    +0.04
    0.07
    668
    +0.03
    0.05
    Negative Logits
    Reviewer
    -0.26
    ij士
    -0.24
     winners
    -0.23
    oval
    -0.23
     disse
    -0.22
     queen
    -0.22
     jurors
    -0.22
    entry
    -0.21
     finalists
    -0.21
    bledon
    -0.21
    POSITIVE LOGITS
    urations
    0.27
    enment
    0.26
    heit
    0.26
    uated
    0.25
     Magicka
    0.24
    uating
    0.24
     Idle
    0.24
     Scrolls
    0.24
    )].
    0.23
     Zap
    0.23
    Activations Density 12.464%

    No Known Activations