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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3752
    Prev
    Next
    INDEX
    Explanations

    a mix of characters from different languages, possibly a language detection algorithm

    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
    288
    +0.14
    0.5%
    649
    +0.14
    0.5%
    302
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.14
    0.05
    45
    +0.14
    0.03
    699
    +0.12
    0.03
    Negative Logits
    merce
    -1.30
    kson
    -1.19
    Äĩ
    -1.04
    ffer
    -1.03
    geries
    -1.02
    atche
    -1.02
    byn
    -1.01
    yip
    -1.00
    ptin
    -0.94
    mson
    -0.94
    POSITIVE LOGITS
    а
    1.26
    и
    1.20
    оÐ
    1.18
    о
    1.09
    ÑĤ
    1.07
    ļ
    1.04
    ±
    1.03
    Ñ
    1.00
    н
    0.96
    Ñĭ
    0.96
    Activations Density 0.314%

    No Known Activations