© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 10762
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal justice, convictions, and law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to criminal convictions and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    echo
    -0.78
    tz
    -0.76
    tel
    -0.71
     Canaver
    -0.69
    ridor
    -0.68
     Deadline
    -0.65
    wang
    -0.65
     Printed
    -0.65
     Telesc
    -0.64
     moistur
    -0.64
    POSITIVE LOGITS
     crimes
    1.82
     misdem
    1.72
     wrongdoing
    1.55
     offenses
    1.55
     offences
    1.55
     crime
    1.51
     criminality
    1.50
     felony
    1.45
     criminal
    1.42
     heinous
    1.40
    Activations Density 0.327%

    No Known Activations