© 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. 610
    Prev
    Next
    INDEX
    Explanations

    requests for comments

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to requests for comments

    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
    soDeliveryDate
    -0.71
    Ranked
    -0.66
     annoy
    -0.60
    ãĤ¨
    -0.60
    Fit
    -0.59
    Skip
    -0.58
    Destroy
    -0.58
     wisely
    -0.57
    Yep
    -0.56
    ledged
    -0.56
    POSITIVE LOGITS
     comment
    1.64
     clarification
    1.22
     comments
    1.09
     interviews
    1.04
     elabor
    1.02
    comment
    1.00
     confirmation
    0.97
     explanation
    0.92
     further
    0.91
     commenting
    0.87
    Activations Density 0.038%

    No Known Activations