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. 6-RES-JB
    6. 23278
    Prev
    Next
    INDEX
    Explanations

    specific keywords related to academic papers or articles

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to articles and formal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azeera
    -0.73
    riched
    -0.72
    elsius
    -0.69
    hemy
    -0.68
    NECT
    -0.68
    ioxide
    -0.66
     Marketable
    -0.65
    orsi
    -0.63
    AFP
    -0.61
    gans
    -0.61
    POSITIVE LOGITS
     itself
    1.00
    iest
    0.77
    ultimate
    0.76
    osphere
    0.76
    liest
    0.74
    iverse
    0.74
    sth
    0.65
     BEFORE
    0.65
     makers
    0.64
     hypothesis
    0.64
    Activations Density 0.609%

    No Known Activations