© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 1985
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to headlines

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    590
    +0.16
    0.5%
    609
    +0.16
    0.5%
    526
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.10
    326
    +0.16
    0.08
    590
    +0.14
    0.04
    Negative Logits
    estern
    -1.01
    urrency
    -0.99
    iable
    -0.98
    ikarp
    -0.98
    ivas
    -0.96
    ersen
    -0.94
    ¬¼
    -0.94
    ija
    -0.94
    heed
    -0.93
    ajor
    -0.93
    POSITIVE LOGITS
    dress
    1.24
    TextColor
    1.17
    ãĥŀ
    1.11
    mast
    1.09
    lined
    1.07
    cloth
    1.00
     proclaiming
    1.00
    deck
    0.99
    LINE
    0.96
    tenance
    0.94
    Activations Density 1.173%

    No Known Activations