© 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. 4-RES-JB
    11. 22540
    Prev
    Next
    INDEX
    Explanations

    words related to legal terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific controversial topics, particularly related to cannibalism and abortion

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

    No Comments

    Negative Logits
     Lawyers
    -0.85
    lli
    -0.82
    tm
    -0.75
    911
    -0.74
    wagen
    -0.72
    ffield
    -0.72
    STEM
    -0.70
    tone
    -0.69
    atility
    -0.68
    erness
    -0.66
    POSITIVE LOGITS
    uate
    0.85
    ibo
    0.74
    uated
    0.73
     cannibal
    0.72
    uity
    0.72
    uating
    0.71
    imation
    0.69
    aste
    0.68
     commod
    0.68
     Corpse
    0.67
    Activations Density 0.030%

    No Known Activations