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. 9-RES-JB
    6. 581
    Prev
    Next
    INDEX
    Explanations

    words related to physical actions like singing, dancing, talking, and walking

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions, particularly the word "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Salvation
    -0.75
     Parenthood
    -0.66
     Libyan
    -0.66
    Instance
    -0.64
     Establishment
    -0.63
     disabling
    -0.62
     Lifetime
    -0.62
     uncanny
    -0.62
    isible
    -0.61
     Gateway
    -0.61
    POSITIVE LOGITS
     pray
    0.98
     interact
    0.91
     behave
    0.90
     communicate
    0.89
     eat
    0.88
     breathe
    0.86
     speak
    0.84
     groom
    0.83
     grow
    0.82
     circulate
    0.82
    Activations Density 0.217%

    No Known Activations