© 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. 4-RES-JB
    11. 9769
    Prev
    Next
    INDEX
    Explanations

    the word "bob" and various names or variations of the name "Cliff" in the document

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and titles

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

    No Comments

    Negative Logits
    ¯¯¯¯
    -0.96
    hip
    -0.91
    uscript
    -0.83
    ufact
    -0.78
    stall
    -0.76
    cial
    -0.72
    ced
    -0.69
    ial
    -0.67
    ual
    -0.67
    wall
    -0.66
    POSITIVE LOGITS
    rities
    0.80
    odox
    0.73
    uzz
    0.70
    herty
    0.70
    abies
    0.70
    iliate
    0.69
    ANY
    0.68
    urses
    0.67
    uggage
    0.65
    riad
    0.65
    Activations Density 0.028%

    No Known Activations