© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1791
    Prev
    Next
    INDEX
    Explanations

    additional information or details mentioned in a document, possibly related to technology or procedures

    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
    623
    +0.13
    0.5%
    451
    +0.13
    0.5%
    642
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    623
    +0.13
    0.06
    408
    +0.13
    0.08
    568
    +0.12
    0.04
    Negative Logits
    lua
    -0.88
     Alone
    -0.87
    cture
    -0.81
    ards
    -0.80
    ese
    -0.78
    naire
    -0.77
    ESE
    -0.77
     """
    -0.77
    uay
    -0.77
     Rampage
    -0.77
    POSITIVE LOGITS
     complication
    1.26
     complications
    1.04
     assistance
    1.03
    ities
    0.98
    judicial
    0.97
     mater
    0.97
     bonus
    0.96
     adjustment
    0.93
     adjustments
    0.93
     expense
    0.92
    Activations Density 1.390%

    No Known Activations