© 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. 35337
    Prev
    Next
    INDEX
    Explanations

    mentions of varying topics related to news and political events

    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
    447
    +0.37
    1.8%
    640
    +0.16
    0.8%
    393
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.37
    0.35
    559
    +0.16
    0.13
    123
    +0.12
    0.15
    Negative Logits
     unemploy
    -0.61
     looms
    -0.61
     spoil
    -0.60
     lodged
    -0.59
    76561
    -0.59
    reon
    -0.58
     endors
    -0.56
     nailed
    -0.56
     bestowed
    -0.55
    :/
    -0.55
    POSITIVE LOGITS
     addition
    1.23
    ventory
    1.16
     spite
    1.16
     contrast
    1.11
    cluding
    1.10
    flation
    1.07
    juries
    1.07
     lieu
    1.04
    herent
    1.03
    jured
    1.02
    Activations Density 12.189%

    No Known Activations