© 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. 12103
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming-related text

    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
    287
    +0.06
    0.4%
    424
    +0.06
    0.4%
    26
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.06
    0.01
    657
    +0.06
    0.01
    604
    +0.05
    0.01
    Negative Logits
     Ratings
    -0.45
     Nadu
    -0.44
    orem
    -0.44
     Reilly
    -0.43
     Turk
    -0.43
    fters
    -0.43
     Badge
    -0.43
    undown
    -0.42
    ģ«
    -0.41
    yden
    -0.40
    POSITIVE LOGITS
    MF
    0.41
    PsyNetMessage
    0.39
    Bloom
    0.39
    sg
    0.39
    ulate
    0.39
    Introduced
    0.39
    IUM
    0.38
    hap
    0.36
     aug
    0.36
    ,,,,,,,,
    0.35
    Activations Density 0.033%

    No Known Activations