© 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. 1-RES-JB
    11. 20454
    Prev
    Next
    INDEX
    Explanations

    references to different forms of abuse, particularly with a focus on child and sexual abuse

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various forms of abuse

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    pard
    -0.70
    amins
    -0.70
     Kinnikuman
    -0.69
    gran
    -0.68
    printed
    -0.67
    ebus
    -0.67
    puter
    -0.66
     Gork
    -0.66
    nee
    -0.65
    prints
    -0.65
    POSITIVE LOGITS
     abuse
    1.27
    abuse
    1.25
     abusing
    1.15
     abused
    1.14
     abuses
    1.10
     Abuse
    1.04
     misuse
    0.88
     abusers
    0.87
    reatment
    0.76
     allegations
    0.73
    Activations Density 0.010%

    No Known Activations