© 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. 4954
    Prev
    Next
    INDEX
    Explanations

    proper names or nicknames

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or specific identifiers, 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 @ 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
    ivity
    -0.95
    sburg
    -0.77
    ive
    -0.76
    ivities
    -0.75
    aic
    -0.71
    ioned
    -0.70
    s
    -0.69
    ees
    -0.68
    ibly
    -0.66
    worthy
    -0.66
    POSITIVE LOGITS
    lda
    1.07
    qua
    0.98
    selage
    0.97
    ÄŁ
    0.97
    jin
    0.91
    vernment
    0.87
    pper
    0.87
    ça
    0.86
    pload
    0.84
    ÃŁ
    0.84
    Activations Density 0.143%

    No Known Activations