Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 11062
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal activities or charges

    oai_token-act-pair · gpt-3.5-turbo

    terms related to criminal activity and offenses

    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
    Whe
    -0.84
     Ratio
    -0.81
     ratio
    -0.77
     ratios
    -0.73
    idges
    -0.72
    Reviewed
    -0.71
    Temperature
    -0.69
     warmed
    -0.68
    Opt
    -0.68
    oration
    -0.67
    POSITIVE LOGITS
     criminal
    3.57
    criminal
    3.11
     Criminal
    2.49
    riminal
    2.21
     criminality
    2.07
     criminals
    2.00
     felony
    1.85
     crime
    1.84
     criminally
    1.82
     Crimes
    1.75
    Activations Density 0.028%

    No Known Activations