© 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. 19807
    Prev
    Next
    INDEX
    Explanations

    mentions of politicians, government officials, and legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    references to judicial authorities and political figures

    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
    ONSORED
    -0.68
    ALLY
    -0.66
    Operation
    -0.66
    ãĥŁ
    -0.64
     Palest
    -0.63
     Loop
    -0.63
    SOURCE
    -0.62
     MAN
    -0.61
     Virus
    -0.61
    FH
    -0.61
    POSITIVE LOGITS
    hips
    1.60
    hip
    1.50
    ervatives
    1.23
    paces
    1.07
    ervative
    1.02
    mith
    0.94
    '
    0.91
    creen
    0.91
    pread
    0.89
    pace
    0.89
    Activations Density 0.101%

    No Known Activations