© 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
    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. 15450
    Prev
    Next
    INDEX
    Explanations

    terms related to criminal activity and legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    references to criminal charges or investigations

    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
    yip
    -1.02
    daq
    -0.83
    pread
    -0.81
    metry
    -0.80
    chell
    -0.79
    galitarian
    -0.79
     Remastered
    -0.78
     Pixie
    -0.75
    zl
    -0.75
    ioned
    -0.71
    POSITIVE LOGITS
    ized
    1.10
     prosecutions
    1.02
     sanction
    1.00
     prosecution
    0.98
    ised
    0.96
     justice
    0.96
     sanctions
    0.95
    izes
    0.95
     enterprises
    0.91
     penalties
    0.91
    Activations Density 0.024%

    No Known Activations