© 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. 2-RES-JB
    11. 9405
    Prev
    Next
    INDEX
    Explanations

    requests for action or assistance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "please."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ARC
    -0.79
    arc
    -0.72
    advertisement
    -0.69
    senal
    -0.66
    existence
    -0.65
    ription
    -0.64
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.64
    perty
    -0.62
    alone
    -0.62
    é¾
    -0.61
    POSITIVE LOGITS
     sir
    0.90
    lyak
    0.78
     pardon
    0.77
     please
    0.77
     note
    0.75
     kindly
    0.74
     excuse
    0.74
     fill
    0.73
     Ignore
    0.73
     Please
    0.73
    Activations Density 0.013%

    No Known Activations