© 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. 7-RES-JB
    11. 3092
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and illegal activities, including investigations, infringements, and violations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    flix
    -0.68
    estones
    -0.63
     apiece
    -0.61
    Legend
    -0.61
    acly
    -0.61
    nesday
    -0.60
    VL
    -0.60
    luster
    -0.60
    tub
    -0.59
    retty
    -0.59
    POSITIVE LOGITS
     unconstitutional
    0.93
     impunity
    0.84
     unjust
    0.84
     perjury
    0.83
     extortion
    0.82
     blackmail
    0.81
     criminal
    0.81
     intimidation
    0.78
     unlawful
    0.78
     coercive
    0.74
    Activations Density 1.183%

    No Known Activations