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

    Neuronpedia

    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. 7821
    Prev
    Next
    INDEX
    Explanations

    requests or lack of response to requests for comments

    oai_token-act-pair · gpt-3.5-turbo

    instances of non-responses 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 @ 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
     beware
    -0.61
    Definition
    -0.60
    vir
    -0.60
    ç¥ŀ
    -0.58
    Ĭ
    -0.58
    selves
    -0.58
     disbanded
    -0.57
    ité
    -0.57
     "$:/
    -0.57
     loser
    -0.56
    POSITIVE LOGITS
     requests
    1.14
     request
    0.98
     emailed
    0.97
     inquiries
    0.95
     telephone
    0.94
     HuffPost
    0.92
     queries
    0.91
     phone
    0.90
     repeated
    0.90
     CNBC
    0.87
    Activations Density 0.068%

    No Known Activations