© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 17695
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to asking or inviting someone to do something

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs that suggest a completion or resolution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åī
    -0.78
    ãĥ¼ãĥ³
    -0.71
    Course
    -0.71
    è¯
    -0.67
     Scotia
    -0.64
    Trend
    -0.63
    Cont
    -0.63
    isol
    -0.62
    Extreme
    -0.59
    Administ
    -0.59
    POSITIVE LOGITS
    ked
    1.12
    lift
    0.96
    king
    0.95
    escription
    0.91
    creen
    0.89
    lass
    0.83
    lasses
    0.82
    hiro
    0.78
    inburgh
    0.78
    kered
    0.78
    Activations Density 0.003%

    No Known Activations