Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 7936
    Prev
    Next
    INDEX
    Explanations

    percentage values related to votes

    oai_token-act-pair · gpt-3.5-turbo

    percentages and voting statistics

    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
    pload
    -0.78
    ©¶æ
    -0.72
    Ĥª
    -0.64
    ycle
    -0.63
    ropolis
    -0.63
    umbered
    -0.60
    acly
    -0.60
    icon
    -0.59
    lio
    -0.58
     Rav
    -0.58
    POSITIVE LOGITS
     disapproval
    1.17
     disapprove
    1.08
     undecided
    1.06
     approval
    1.02
     favorable
    1.01
     unfavorable
    1.01
     plurality
    0.98
     support
    0.98
     favor
    0.97
     apiece
    0.97
    Activations Density 0.067%

    No Known Activations