© 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. 0-RES-JB
    6. 7903
    Prev
    Next
    INDEX
    Explanations

    mentions of legal professions, specifically prosecutors

    oai_token-act-pair · gpt-3.5-turbo

    references to legal officials, specifically prosecutors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ect
    -0.62
     XP
    -0.60
     Ships
    -0.59
    ripp
    -0.59
     Origin
    -0.59
    origin
    -0.58
    houses
    -0.58
    ships
    -0.58
     vertical
    -0.57
    rf
    -0.57
    POSITIVE LOGITS
     prosecutor
    3.65
     Prosecutor
    3.09
     prosecutors
    2.48
    Prosecut
    2.38
     Prosecutors
    2.10
    Prosecutors
    2.06
     prosecuting
    1.92
     prosecut
    1.88
     Prosecut
    1.86
     prosecution
    1.77
    Activations Density 0.018%

    No Known Activations