© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 24304
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal activity and law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    references to offenders and criminals, particularly in the context of sexual crimes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    zl
    -0.82
     increments
    -0.70
    ahon
    -0.70
     Maiden
    -0.70
    Ħ¢
    -0.70
     Fork
    -0.65
    printed
    -0.65
    ilde
    -0.64
    agra
    -0.64
     Winds
    -0.63
    POSITIVE LOGITS
     mastermind
    1.03
     who
    0.99
     beware
    0.98
     prey
    0.97
     sentenced
    0.89
     hiding
    0.88
     perpetrated
    0.86
     lurking
    0.85
     whom
    0.85
    gery
    0.83
    Activations Density 0.135%

    No Known Activations