© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 7128
    Prev
    Next
    INDEX
    Explanations

    mentions of different forms of sexual assault, including allegations, reports, and discussions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sexual assault and harassment

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

    No Comments

    Negative Logits
    peed
    -0.75
    IPS
    -0.74
    peror
    -0.74
    WARD
    -0.68
    AY
    -0.68
    AIR
    -0.68
    æ°
    -0.67
    KC
    -0.67
    XM
    -0.65
    ãĤ©
    -0.65
    POSITIVE LOGITS
    Sexual
    0.96
     Rape
    0.90
     allegations
    0.87
     rape
    0.86
     perpetrated
    0.83
     victims
    0.79
     raped
    0.79
     sexually
    0.79
     abuse
    0.79
     allegation
    0.78
    Activations Density 0.069%

    No Known Activations