© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9329
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to legal and criminal topics, particularly concerning juveniles

    oai_token-act-pair · gpt-3.5-turbo

    references to juveniles and juvenile-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cross
    -0.75
    ãĤ¡
    -0.73
    ++++++++++++++++
    -0.73
    bsite
    -0.72
    ding
    -0.71
    âķIJ
    -0.71
    anyahu
    -0.71
     damned
    -0.69
    SOURCE
    -0.69
    ters
    -0.68
    POSITIVE LOGITS
     delinqu
    1.43
     delinquent
    1.18
     Juven
    0.95
     males
    0.85
     Gohan
    0.82
     Swim
    0.82
    ishly
    0.82
     detention
    0.80
     offenders
    0.76
     females
    0.73
    Activations Density 0.033%

    No Known Activations