© 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. 2505
    Prev
    Next
    INDEX
    Explanations

    statements related to funding support for research projects

    oai_token-act-pair · gpt-3.5-turbo

    references to funding sources and support for research

    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
    iquette
    -0.95
     brut
    -0.77
     haunt
    -0.74
    ãĥĥãĥī
    -0.74
    gamer
    -0.71
     boun
    -0.71
    hooting
    -0.69
     cruising
    -0.69
    iens
    -0.69
    engers
    -0.69
    POSITIVE LOGITS
     grants
    1.61
     grant
    1.59
     Grants
    1.56
     NIH
    1.52
     funding
    1.37
     Funding
    1.35
    Grant
    1.35
     Grant
    1.35
     funds
    1.26
     scholarships
    1.22
    Activations Density 0.275%

    No Known Activations