© 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. 11-RES-JB
    11. 22633
    Prev
    Next
    INDEX
    Explanations

    requests for actions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to weekly actionable items or suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amaru
    -0.71
    ante
    -0.64
    antes
    -0.63
    esville
    -0.62
    adr
    -0.60
    istically
    -0.60
    obyl
    -0.59
    ilts
    -0.59
    omes
    -0.58
    orously
    -0.57
    POSITIVE LOGITS
     Everyday
    0.70
     Week
    0.64
     Minute
    0.64
     weekday
    0.60
    Self
    0.60
     week
    0.58
    sent
    0.57
     minute
    0.57
     Daily
    0.56
     reaction
    0.56
    Activations Density 0.036%

    No Known Activations