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. 8-RES-JB
    6. 4515
    Prev
    Next
    INDEX
    Explanations

    references to pubs or public houses

    oai_token-act-pair · gpt-3.5-turbo

    mentions of pubs or similar establishments

    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
     Gaia
    -0.72
    OHN
    -0.71
     EFF
    -0.69
    llor
    -0.69
    IRD
    -0.69
     Archangel
    -0.67
     autom
    -0.63
    ylum
    -0.63
    xual
    -0.61
     Reson
    -0.61
    POSITIVE LOGITS
    lish
    1.43
    lique
    1.41
    lishing
    1.39
    lishes
    1.37
    lisher
    1.32
    escent
    1.21
    bing
    1.11
    lik
    1.03
    bed
    0.95
    bish
    0.94
    Activations Density 0.029%

    No Known Activations