© 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. 2-RES-JB
    11. 9182
    Prev
    Next
    INDEX
    Explanations

    legal or criminal terms such as "arrest," "charged," and "felony."

    oai_token-act-pair · gpt-3.5-turbo

    legal terminology and references to criminal charges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Babel
    -0.73
    phil
    -0.73
    poll
    -0.70
     2030
    -0.70
    iasm
    -0.70
    natureconservancy
    -0.69
    enment
    -0.69
    Econom
    -0.69
     2050
    -0.69
     ç¥ŀ
    -0.67
    POSITIVE LOGITS
     manslaughter
    1.16
     misdemeanor
    1.04
     offences
    1.04
     felony
    1.02
     perjury
    1.00
     homicide
    0.95
     prosecution
    0.95
     felon
    0.94
     crimes
    0.93
     aggravated
    0.93
    Activations Density 1.401%

    No Known Activations