© 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. 32365
    Prev
    Next
    INDEX
    Explanations

    Dungeons and dragons game items, actions, and characters

    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
    730
    +0.12
    0.6%
    407
    +0.09
    0.4%
    170
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    -0.07
    640
    +0.09
    0.13
    713
    +0.09
    0.04
    Negative Logits
    ĸļ
    -0.65
    racuse
    -0.61
     Berger
    -0.61
    ospace
    -0.61
    onite
    -0.61
    oles
    -0.59
    ority
    -0.58
    cules
    -0.58
    omez
    -0.58
    edIn
    -0.57
    POSITIVE LOGITS
    ribute
    0.64
    OPE
    0.62
    resp
    0.60
    ij士
    0.60
    urion
    0.59
    ranged
    0.59
    IV
    0.58
    way
    0.58
    protected
    0.58
    @@
    0.56
    Activations Density 2.298%

    No Known Activations