© 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. 0-RES-JB
    11. 8198
    Prev
    Next
    INDEX
    Explanations

    legal and criminal offenses

    oai_token-act-pair · gpt-3.5-turbo

    terms related to criminal offenses and legal categories

    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
    ulus
    -0.66
     cho
    -0.63
     echo
    -0.62
    aline
    -0.61
    Phys
    -0.61
     illusion
    -0.60
     CGI
    -0.60
    ma
    -0.59
    aran
    -0.59
    CG
    -0.58
    POSITIVE LOGITS
     offenses
    3.05
     offences
    3.04
     crimes
    2.14
     misdem
    1.86
     offenders
    1.86
     violations
    1.85
     Crimes
    1.67
     prosecutions
    1.53
     thefts
    1.53
     breaches
    1.50
    Activations Density 0.013%

    No Known Activations