© 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 EvalsExportsAPI 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. 12360
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions of physical actions or events happening in a specific storyline

    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
    393
    +0.19
    0.7%
    323
    +0.18
    0.7%
    640
    +0.18
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    124
    +0.19
    0.07
    152
    +0.18
    0.07
    314
    +0.18
    0.02
    Negative Logits
     Dickinson
    -0.85
     Britann
    -0.84
    idable
    -0.83
     crept
    -0.82
     incorpor
    -0.81
    ertodd
    -0.80
    ersen
    -0.80
     Rohingya
    -0.79
     lined
    -0.79
     penetrated
    -0.79
    POSITIVE LOGITS
    cont
    1.38
    distance
    1.29
    english
    1.28
    speech
    1.26
    sight
    1.26
    human
    1.25
    function
    1.24
    earth
    1.24
    advertising
    1.24
    pair
    1.22
    Activations Density 0.858%

    No Known Activations