© 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. 4949
    Prev
    Next
    INDEX
    Explanations

    phrases related to legality and prohibition

    oai_token-act-pair · gpt-3.5-turbo

    references to legality or illegality of activities within various jurisdictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    addle
    -0.76
     resil
    -0.74
    rious
    -0.72
     frustrations
    -0.68
    forward
    -0.67
    leeve
    -0.67
     pessimistic
    -0.65
    ded
    -0.64
    hett
    -0.63
     disillusion
    -0.63
    POSITIVE LOGITS
     whatsoever
    0.73
     minors
    0.71
     foreseeable
    0.71
     Parenthood
    0.68
     prohibiting
    0.67
     confines
    0.67
     Constitutional
    0.67
     Sanct
    0.67
     jurisdictions
    0.66
     statute
    0.66
    Activations Density 0.445%

    No Known Activations