© 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. 24078
    Prev
    Next
    INDEX
    Explanations

    names or pronouns referring to people

    oai_token-act-pair · gpt-3.5-turbo

    references to people and their interactions

    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
    NetMessage
    -0.45
     Pwr
    -0.38
    ĵĺ
    -0.34
     WATCHED
    -0.33
     ///
    -0.30
    VIDIA
    -0.29
    RESULTS
    -0.28
    ongyang
    -0.28
     Pastebin
    -0.28
    iosyn
    -0.28
    POSITIVE LOGITS
    ividual
    0.39
     onward
    0.33
    iversary
    0.32
    orf
    0.31
    gins
    0.30
    fur
    0.30
    iazep
    0.30
    hower
    0.29
     lasts
    0.29
    ierre
    0.29
    Activations Density 2.319%

    No Known Activations