© 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. 1734
    Prev
    Next
    INDEX
    Explanations

    names or proper nouns related to specific places or individuals

    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
    549
    +0.18
    0.8%
    649
    +0.12
    0.5%
    193
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.18
    0.10
    57
    +0.12
    0.08
    232
    +0.11
    0.09
    Negative Logits
    è»
    -0.93
    士
    -0.89
    EMENT
    -0.86
    è¯
    -0.81
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.81
    ä¹ĭ
    -0.80
    EED
    -0.80
    åij
    -0.79
    IFIED
    -0.79
     IMAGES
    -0.79
    POSITIVE LOGITS
    terness
    1.08
    una
    1.05
    ighty
    1.04
    ols
    1.02
    omin
    0.99
    oby
    0.99
    umar
    0.98
    rows
    0.98
    combe
    0.97
    roman
    0.96
    Activations Density 1.371%

    No Known Activations