© 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. 35801
    Prev
    Next
    INDEX
    Explanations

    specific names, possibly related to individuals

    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
    240
    +0.12
    0.6%
    343
    +0.10
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.23
    48
    +0.10
    0.13
    288
    +0.10
    0.22
    Negative Logits
    resso
    -0.72
    estern
    -0.70
    abwe
    -0.68
    ably
    -0.66
    IBLE
    -0.65
    ision
    -0.64
    ingham
    -0.62
    rane
    -0.61
    ablishment
    -0.60
    isively
    -0.60
    POSITIVE LOGITS
    vez
    0.72
    jas
    0.70
    yards
    0.67
    heed
    0.66
    alia
    0.65
    idy
    0.65
     Kut
    0.64
    strate
    0.64
    yard
    0.62
    amia
    0.61
    Activations Density 7.442%

    No Known Activations