© 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 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. 3-RES-JB
    11. 11635
    Prev
    Next
    INDEX
    Explanations

    terms related to instances of sexual assault

    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 @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aer
    -0.70
     Objective
    -0.67
    ãĤ©
    -0.66
     snipp
    -0.65
    IPS
    -0.64
    ãĥķãĤ©
    -0.63
    xxxxxxxx
    -0.63
     newsp
    -0.62
    peror
    -0.62
    coat
    -0.62
    POSITIVE LOGITS
     abuse
    0.95
     rape
    0.89
     allegations
    0.86
     slurs
    0.83
    assment
    0.82
     inappropriately
    0.81
    abuse
    0.81
     perpetrated
    0.80
     victims
    0.80
    Sexual
    0.79
    Activations Density 0.066%

    No Known Activations