© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 8744
    Prev
    Next
    INDEX
    Explanations

    the name "Tom" in various contexts or mentions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Tom."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gazette
    -0.77
    shapeshifter
    -0.76
    Ĥİ
    -0.71
    wrapper
    -0.70
    xual
    -0.68
    draft
    -0.68
    ĸļ
    -0.67
    ãģį
    -0.65
    journal
    -0.64
    FUL
    -0.63
    POSITIVE LOGITS
    atoes
    1.20
    Tom
    1.03
     Clancy
    0.97
    itan
    0.96
    oya
    0.95
    orrow
    0.90
    atsu
    0.89
     Cruise
    0.88
    oshenko
    0.86
    atis
    0.84
    Activations Density 0.013%

    No Known Activations