© 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 Local
    9. 6-RES_SCL-AJT
    11. 40553
    Prev
    Next
    INDEX
    Explanations

    Cyrillic characters with patterns and variations in text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    +0.15
    0.6%
    655
    +0.13
    0.5%
    50
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.15
    0.28
    50
    +0.13
    0.14
    107
    +0.12
    0.06
    Negative Logits
     immersion
    -0.76
     specificity
    -0.74
    hyde
    -0.72
     shortest
    -0.71
     plurality
    -0.71
     gestation
    -0.70
    ividual
    -0.70
    xus
    -0.69
     reluct
    -0.68
     Granger
    -0.67
    POSITIVE LOGITS
    ÑĢ
    1.16
    е
    1.09
    а
    1.03
    Ñĥ
    1.01
    и
    1.01
    л
    1.01
    оÐ
    0.99
    Ð
    0.98
    н
    0.96
    º
    0.95
    Activations Density 12.286%

    No Known Activations