© 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. 6984
    Prev
    Next
    INDEX
    Explanations

    references to specific names such as "McDonnell" and "Parsons"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the name "McDonnell" and "Parsons."

    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
    76561
    -0.67
    ablishment
    -0.65
     Flavoring
    -0.65
    ught
    -0.63
    doors
    -0.62
    vent
    -0.62
    lier
    -0.62
    bos
    -0.62
    unin
    -0.61
    Tok
    -0.61
    POSITIVE LOGITS
     McDonnell
    0.94
    Donnell
    0.93
    emouth
    0.86
    fman
    0.78
    ©¶æ¥µ
    0.76
     Douglas
    0.75
    issance
    0.75
    hurst
    0.70
    enthal
    0.67
    shire
    0.66
    Activations Density 0.014%

    No Known Activations