© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3322
    Prev
    Next
    INDEX
    Explanations

    language related to requests or instructions, such as asking for tips, making submissions, or leaving comments

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating the sharing or requesting of information and feedback

    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
    psc
    -0.86
    gdala
    -0.76
    artisan
    -0.76
    iably
    -0.75
    itone
    -0.74
    obyl
    -0.72
    ©¶æ¥µ
    -0.70
    ibr
    -0.69
    olate
    -0.68
    gado
    -0.68
    POSITIVE LOGITS
     tips
    1.28
     announcements
    1.25
     explanations
    1.23
     tutorials
    1.22
     recommendations
    1.22
     suggestions
    1.21
     endorsements
    1.20
     corrections
    1.15
     additions
    1.13
     screenshots
    1.13
    Activations Density 0.165%

    No Known Activations