© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 4076
    Prev
    Next
    INDEX
    Explanations

    the word "Chaplin."

    oai_token-act-pair · gpt-3.5-turbo

    references to Charlie Chaplin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ports
    -0.87
    WARD
    -0.81
    ences
    -0.76
    lund
    -0.76
    enced
    -0.74
    GGGGGGGG
    -0.71
    nings
    -0.69
    gence
    -0.69
    ENC
    -0.68
    agles
    -0.67
    POSITIVE LOGITS
    bara
    0.94
    anooga
    0.90
    acters
    0.86
    plain
    0.85
    ron
    0.82
    agne
    0.80
    ocobo
    0.76
    illin
    0.76
    icago
    0.76
    osen
    0.74
    Activations Density 0.069%

    No Known Activations