© 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. 8-RES-JB
    11. 6960
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or criminal activities involving juveniles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to juvenile justice and delinquency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cross
    -0.79
    pr
    -0.77
    lessly
    -0.72
    ding
    -0.70
    ãĥ©
    -0.68
    sts
    -0.67
    witz
    -0.67
    prise
    -0.66
    acle
    -0.64
    pert
    -0.63
    POSITIVE LOGITS
     delinqu
    1.34
     delinquent
    1.07
     Juven
    0.86
     detention
    0.83
     Swim
    0.79
    ishly
    0.78
     Detention
    0.76
    egal
    0.73
     males
    0.72
    ellar
    0.70
    Activations Density 0.049%

    No Known Activations