© 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. 35131
    Prev
    Next
    INDEX
    Explanations

    references to the Marvel character Thor

    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
    +0.13
    0.6%
    269
    +0.10
    0.5%
    139
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.22
    75
    +0.10
    0.09
    343
    +0.10
    0.08
    Negative Logits
    pring
    -0.68
    mble
    -0.67
    cloth
    -0.62
    print
    -0.61
    teen
    -0.61
    ablishment
    -0.60
     Fool
    -0.60
    pace
    -0.59
    ardy
    -0.59
    ateur
    -0.59
    POSITIVE LOGITS
     Ragnarok
    0.84
     Jinn
    0.74
    etheus
    0.71
    icum
    0.70
    imus
    0.69
    igon
    0.67
    arium
    0.67
    istries
    0.67
    osaurs
    0.61
    inus
    0.61
    Activations Density 8.090%

    No Known Activations