© 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. 502
    Prev
    Next
    INDEX
    Explanations

    mentions of specific nationalities or professions

    oai_token-act-pair · gpt-3.5-turbo

    entities related to individuals involved in various social, political, and legal contexts

    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
    ptions
    -0.76
    ologies
    -0.70
    mins
    -0.66
    akings
    -0.65
     winners
    -0.65
     lows
    -0.64
     periods
    -0.64
    ippers
    -0.64
     Pieces
    -0.64
     Racial
    -0.62
    POSITIVE LOGITS
    alyst
    0.91
     named
    0.91
     who
    0.89
     staffer
    0.79
     acquaintance
    0.76
     whose
    0.76
     colleague
    0.73
    worker
    0.73
    friend
    0.72
    looking
    0.70
    Activations Density 0.402%

    No Known Activations