Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 10912
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to body parts used colloquially for emphasis or as insults

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the word "ass."

    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
     Kubrick
    -0.74
    MSN
    -0.73
     Welsh
    -0.66
     Alzheimer
    -0.61
     SIG
    -0.59
     Kramer
    -0.59
     PBS
    -0.58
    Interested
    -0.58
     methyl
    -0.58
     Parkinson
    -0.57
    POSITIVE LOGITS
    imilation
    1.53
    holes
    1.20
    sembly
    1.05
     cheeks
    1.01
    itude
    1.00
    ortment
    1.00
    assin
    0.98
    aul
    0.98
    ails
    0.98
    umption
    0.97
    Activations Density 0.009%

    No Known Activations