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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 7595
    Prev
    Next
    INDEX
    Explanations

    terms related to legal actions, specifically the issuance or violation of gag orders

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal restrictions or orders

    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
     Firm
    -0.63
     accur
    -0.60
    anqu
    -0.59
     priced
    -0.59
     cryst
    -0.58
    accompan
    -0.57
    xual
    -0.57
     Cald
    -0.57
     Hurricanes
    -0.55
    signed
    -0.55
    POSITIVE LOGITS
    glers
    1.44
    gers
    0.94
     gag
    0.89
    gap
    0.89
    liest
    0.88
    acious
    0.81
    bub
    0.80
    ulkan
    0.78
     reflex
    0.78
     reel
    0.77
    Activations Density 0.017%

    No Known Activations