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. 7-RES-JB
    6. 4620
    Prev
    Next
    INDEX
    Explanations

    names of people, particularly Byron, Heath, and Helen

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awaru
    -0.86
    ool
    -0.78
    iatrics
    -0.78
    rosse
    -0.77
    arb
    -0.77
    osition
    -0.76
    eral
    -0.70
    anity
    -0.69
    iatric
    -0.69
    iggurat
    -0.69
    POSITIVE LOGITS
    crow
    0.81
    phal
    0.77
    forth
    0.75
    tti
    0.73
    math
    0.71
    borough
    0.69
    burn
    0.68
    cock
    0.66
    IGHTS
    0.66
    bars
    0.66
    Activations Density 0.059%

    No Known Activations