© 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
    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. 17343
    Prev
    Next
    INDEX
    Explanations

    mentions of legal proceedings and individuals involved in legal cases

    oai_token-act-pair · gpt-3.5-turbo

    references to legal authorities and prosecution in judicial contexts

    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
    76561
    -0.80
    odes
    -0.75
    wash
    -0.74
    ombat
    -0.72
    votes
    -0.71
    obyl
    -0.69
    oken
    -0.69
    birth
    -0.68
    erd
    -0.67
    ontent
    -0.67
    POSITIVE LOGITS
     prosecuting
    1.16
     indicted
    1.14
     prosecutor
    1.06
     allege
    1.05
     prosecutors
    1.02
     prosecuted
    1.02
     alleges
    0.96
     indict
    0.94
     prosecution
    0.92
     indictment
    0.92
    Activations Density 0.075%

    No Known Activations