© 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. 11-RES-JB
    11. 2165
    Prev
    Next
    INDEX
    Explanations

    phrases prompting the audience to share or submit their own content or feedback

    oai_token-act-pair · gpt-3.5-turbo

    references to user submissions or contributions

    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
    forth
    -1.00
    mination
    -0.82
    pher
    -0.76
    ©¶æ
    -0.76
    icably
    -0.71
     Secondly
    -0.67
    ça
    -0.65
    hered
    -0.63
    mir
    -0.63
    pheus
    -0.62
    POSITIVE LOGITS
     favourite
    1.17
     favorite
    1.13
     favorites
    1.13
     suggestions
    1.09
     favourites
    1.08
     own
    1.06
     imagination
    1.02
     thoughts
    1.01
     Favorite
    0.95
     questions
    0.94
    Activations Density 0.104%

    No Known Activations