© 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. 32299
    Prev
    Next
    INDEX
    Explanations

    technical and scientific information

    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
    736
    +0.16
    0.7%
    447
    +0.12
    0.5%
    420
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.16
    0.10
    659
    +0.12
    0.11
    373
    +0.12
    -0.18
    Negative Logits
    Interstitial
    -0.89
    CLOSE
    -0.86
    LEASE
    -0.85
    Magikarp
    -0.83
    REDACTED
    -0.79
     âĢ¦"
    -0.78
    eers
    -0.77
    xual
    -0.75
     [&
    -0.74
    è£ħ
    -0.73
    POSITIVE LOGITS
    endish
    1.00
    oslav
    0.92
    imar
    0.91
    adier
    0.89
    ford
    0.83
    adian
    0.83
    wich
    0.82
    erson
    0.81
    abit
    0.80
    estone
    0.80
    Activations Density 10.885%

    No Known Activations