© 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. 8-RES-JB
    11. 3326
    Prev
    Next
    INDEX
    Explanations

    terms related to criminal convictions and legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    terms related to criminal convictions

    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
    char
    -0.86
    borg
    -0.83
    ãĥ£
    -0.79
    gm
    -0.78
    sonian
    -0.78
    ard
    -0.77
    cott
    -0.75
    rup
    -0.75
    mega
    -0.73
    roc
    -0.72
    POSITIVE LOGITS
     stemming
    0.88
    ary
    0.86
     arising
    0.77
    aries
    0.73
     arose
    0.72
    imei
    0.71
     Guarant
    0.71
     Cousins
    0.69
     incurred
    0.68
     arises
    0.67
    Activations Density 0.188%

    No Known Activations