© 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. 6-RES-JB
    11. 9883
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement agencies or sheriffs in various counties

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms of the word "sheriff."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stream
    -0.85
    flows
    -0.84
    oldemort
    -0.78
    Sov
    -0.78
    FY
    -0.77
    yz
    -0.74
    Reviewer
    -0.74
    yip
    -0.73
    ENN
    -0.70
    verted
    -0.69
    POSITIVE LOGITS
     Office
    1.11
     Department
    1.03
     office
    0.95
     deputies
    0.93
     department
    0.92
     offices
    0.89
     Association
    0.88
     Mansion
    0.85
     Bureau
    0.82
     mansion
    0.81
    Activations Density 0.041%

    No Known Activations