© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10231
    Prev
    Next
    INDEX
    Explanations

    mentions of authority figures or important individuals

    oai_token-act-pair · gpt-3.5-turbo

    themes related to political accountability and criticism

    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
    etc
    -0.67
    wind
    -0.62
    tz
    -0.62
    rup
    -0.61
    bats
    -0.59
    ATA
    -0.57
    orer
    -0.54
    hound
    -0.53
    ieve
    -0.53
    aud
    -0.52
    POSITIVE LOGITS
     principally
    0.93
     chiefly
    0.84
     primarily
    0.83
     includ
    0.79
     accompanied
    0.78
     mainly
    0.77
    mostly
    0.76
    accompanied
    0.74
     mostly
    0.74
     preceded
    0.70
    Activations Density 1.164%

    No Known Activations