© 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. 8-RES-JB
    11. 922
    Prev
    Next
    INDEX
    Explanations

    references to the name "Chaplin"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Charlie Chaplin" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ports
    -0.71
    enced
    -0.70
    WARD
    -0.70
    ative
    -0.65
    nings
    -0.65
    ENC
    -0.65
    agles
    -0.64
    ENCE
    -0.64
    aments
    -0.63
    Accessory
    -0.63
    POSITIVE LOGITS
    plain
    1.17
    anooga
    1.03
    plin
    1.00
    acters
    0.92
    unin
    0.89
    bara
    0.88
    osen
    0.86
    ocobo
    0.85
    ron
    0.82
    isel
    0.81
    Activations Density 0.077%

    No Known Activations