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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 17378
    Prev
    Next
    INDEX
    Explanations

    keywords related to the presence or description of mud

    oai_token-act-pair · gpt-3.5-turbo

    references to "mud."

    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
    yright
    -0.78
    IGHT
    -0.77
    inyl
    -0.71
    ibel
    -0.70
    Sax
    -0.69
    ENCE
    -0.66
     Lauder
    -0.66
     Witness
    -0.66
    ISE
    -0.65
    zona
    -0.65
    POSITIVE LOGITS
    geon
    0.94
    urai
    0.84
    hole
    0.82
     raft
    0.80
    fish
    0.79
    bowl
    0.77
    tro
    0.76
    alore
    0.76
    mers
    0.76
    bat
    0.76
    Activations Density 0.086%

    No Known Activations