© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 20208
    Prev
    Next
    INDEX
    Explanations

    opportunities or events that are rare or unique in a lifetime

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating rarity or exceptional occurrences

    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
    orously
    -0.67
     Cosponsors
    -0.62
    andise
    -0.62
    igl
    -0.61
    umbn
    -0.60
    aciously
    -0.57
    ById
    -0.56
    ãĥ³ãĤ¸
    -0.55
    essor
    -0.55
    appropriately
    -0.55
    POSITIVE LOGITS
    !--
    0.70
     happens
    0.68
    !!!
    0.66
     ;)
    0.66
     :(
    0.65
    !!!!!
    0.64
    !
    0.64
     Suppose
    0.63
     :)
    0.63
    !!
    0.62
    Activations Density 0.827%

    No Known Activations