© 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. 12873
    Prev
    Next
    INDEX
    Explanations

    programming code strings containing technical terms and functions

    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
    447
    +0.23
    0.8%
    167
    +0.17
    0.5%
    83
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.23
    0.06
    31
    +0.17
    0.07
    640
    +0.15
    0.10
    Negative Logits
    accompan
    -1.12
     CoC
    -1.06
    hedon
    -1.04
    idelines
    -1.02
    ModLoader
    -1.01
    comings
    -0.96
    utterstock
    -0.94
    apixel
    -0.93
    arenthood
    -0.91
     mosqu
    -0.91
    POSITIVE LOGITS
    ["
    1.35
    ("
    1.26
    ();
    1.14
     :=
    1.12
     +=
    1.07
    ----------------------------------------------------------------
    1.06
     //
    1.04
     ();
    1.02
    Print
    1.01
    ----------
    0.99
    Activations Density 1.224%

    No Known Activations