© 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. 32387
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Bill Gates"

    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
    525
    +0.04
    0.6%
    657
    +0.03
    0.5%
    223
    +0.03
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    525
    +0.04
    0.08
    234
    +0.03
    0.08
    241
    +0.03
    0.07
    Negative Logits
    RANT
    -0.19
    itious
    -0.18
    journal
    -0.18
     supervisors
    -0.18
     estab
    -0.18
     Shooter
    -0.17
     Salem
    -0.17
     prosecut
    -0.17
    ptin
    -0.16
    inance
    -0.16
    POSITIVE LOGITS
    heed
    0.30
    forth
    0.23
    nan
    0.21
    nard
    0.21
    ilon
    0.21
    quad
    0.21
    ham
    0.20
     bowls
    0.20
     Gates
    0.20
    sworth
    0.20
    Activations Density 7.245%

    No Known Activations