© 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. 22608
    Prev
    Next
    INDEX
    Explanations

    references to specific names or entities with initials

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'J' followed by a period

    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
    holders
    -0.69
    iture
    -0.68
    fman
    -0.68
    terior
    -0.66
    vana
    -0.65
    auga
    -0.64
    chwitz
    -0.64
    aults
    -0.63
    agascar
    -0.63
    milo
    -0.62
    POSITIVE LOGITS
    ournal
    0.92
     Edgar
    0.85
     Sawyer
    0.84
    Crew
    0.83
     Jonah
    0.78
    Ax
    0.78
     Marriott
    0.74
    Lo
    0.74
     Reilly
    0.71
     Simpson
    0.71
    Activations Density 0.043%

    No Known Activations