© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 2194
    Prev
    Next
    INDEX
    Explanations

    mentions of guilty pleas or admissions of wrongdoing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "guilty" in relation to legal or criminal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adish
    -0.76
    edia
    -0.71
    pid
    -0.67
    nic
    -0.67
    dos
    -0.65
     Dull
    -0.64
    inth
    -0.64
    osi
    -0.64
    arist
    -0.63
    care
    -0.63
    POSITIVE LOGITS
     plea
    0.94
     verdict
    0.89
     guilty
    0.85
     Guilty
    0.83
    icts
    0.80
     manslaughter
    0.80
     probation
    0.77
     perjury
    0.76
    istrates
    0.74
     bribery
    0.73
    Activations Density 0.028%

    No Known Activations