Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 8554
    Prev
    Next
    INDEX
    Explanations

    mentions of arrests or criminal charges in news articles

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of arrests and related legal terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aws
    -0.76
    paren
    -0.74
     Explicit
    -0.72
    advertising
    -0.69
    rio
    -0.64
    tick
    -0.64
    inction
    -0.64
    %%%%
    -0.63
    inct
    -0.63
    access
    -0.63
    POSITIVE LOGITS
     sentenced
    1.33
     fined
    1.31
     interrogated
    1.30
     transported
    1.23
     jailed
    1.19
     deported
    1.18
     charged
    1.18
     booked
    1.17
     flown
    1.17
     indicted
    1.12
    Activations Density 0.108%

    No Known Activations