© 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. 3-RES-JB
    11. 15207
    Prev
    Next
    INDEX
    Explanations

    last names of individuals mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly in the entertainment industry

    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
    gerald
    -0.94
    untu
    -0.83
    pled
    -0.82
    rator
    -0.80
    riage
    -0.79
    rament
    -0.76
    riet
    -0.75
    DCS
    -0.73
    ffee
    -0.72
    ctor
    -0.72
    POSITIVE LOGITS
     Glover
    0.93
     Zimmer
    0.87
    schild
    0.76
     GOODMAN
    0.75
     Osw
    0.74
    phrine
    0.72
    ĸļ
    0.71
    xual
    0.65
    stan
    0.65
     tones
    0.65
    Activations Density 0.023%

    No Known Activations