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

    Neuronpedia

    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. 2-RES-JB
    11. 12673
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or investigative proceedings

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal inquiries and officials involved in investigating deaths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eworld
    -0.76
    76561
    -0.75
    achu
    -0.72
     Stars
    -0.70
    auri
    -0.69
    Torrent
    -0.69
     Buc
    -0.68
    endor
    -0.67
    atan
    -0.66
    OPA
    -0.66
    POSITIVE LOGITS
     inquest
    1.42
     coroner
    1.39
     coron
    0.85
     jury
    0.77
     verdict
    0.75
     hemor
    0.75
     overdose
    0.74
    itial
    0.73
     plateau
    0.71
    mortem
    0.71
    Activations Density 0.010%

    No Known Activations