© 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. 12206
    Prev
    Next
    INDEX
    Explanations

    items that are subject to change

    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
    608
    +0.06
    0.5%
    471
    +0.06
    0.4%
    718
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.06
    0.04
    90
    +0.06
    0.03
    385
    +0.06
    0.03
    Negative Logits
    aed
    -0.46
    alk
    -0.46
    started
    -0.44
    bowl
    -0.44
    retty
    -0.44
    iatus
    -0.43
    hots
    -0.42
    arten
    -0.42
    earth
    -0.42
    esome
    -0.41
    POSITIVE LOGITS
     frequent
    0.46
     continual
    0.44
    ilings
    0.44
     constant
    0.42
     negotiation
    0.41
     construct
    0.40
     regard
    0.39
     varying
    0.39
     revision
    0.39
     conc
    0.38
    Activations Density 0.271%

    No Known Activations