© 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. 10-RES-JB
    11. 12340
    Prev
    Next
    INDEX
    Explanations

    phrases indicating judgment or evaluation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe situations involving explanations or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (?,
    -0.77
    ,[
    -0.77
    ',
    -0.77
    iership
    -0.71
    ,'
    -0.69
    ?",
    -0.69
     ',
    -0.66
    !",
    -0.63
    `,
    -0.63
    ",
    -0.61
    POSITIVE LOGITS
     applause
    0.81
    .).
    0.79
     laughs
    0.71
    >.
    0.70
    enegger
    0.68
     understatement
    0.65
    .</
    0.65
     adding
    0.64
     chuck
    0.62
     laughter
    0.62
    Activations Density 0.276%

    No Known Activations