© 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. 8-RES-JB
    11. 24205
    Prev
    Next
    INDEX
    Explanations

    actions involving physical contact and aggression, such as grabbing, punching, and holding

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of physical violence and aggression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Quantity
    -0.74
     Paste
    -0.65
    Reviewer
    -0.64
     Printed
    -0.61
     obser
    -0.59
    IENT
    -0.59
     Majority
    -0.59
     plurality
    -0.58
    apter
    -0.57
     Diver
    -0.57
    POSITIVE LOGITS
     whom
    0.86
    agher
    0.83
    atically
    0.72
     kissing
    0.68
     raping
    0.68
     verbally
    0.68
     asking
    0.67
    tics
    0.67
     accusing
    0.67
     knocking
    0.67
    Activations Density 0.599%

    No Known Activations