© 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. 7-RES-JB
    11. 1766
    Prev
    Next
    INDEX
    Explanations

    dichotomies or distinctions between two or more options or categories

    oai_token-act-pair · gpt-3.5-turbo

    references to categorizations and divisions within topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Beast
    -0.76
    DERR
    -0.74
     Andromeda
    -0.74
    uddin
    -0.69
    bats
    -0.67
    ebook
    -0.66
    ocaust
    -0.65
    ãĤ¼ãĤ¦ãĤ¹
    -0.63
    UNE
    -0.63
    Downloadha
    -0.63
    POSITIVE LOGITS
    :-
    0.93
    %:
    0.88
     viz
    0.88
     simultaneously
    0.77
     distinct
    0.73
    :(
    0.70
    :
    0.69
    ):
    0.69
     concurrently
    0.68
    :'
    0.68
    Activations Density 0.169%

    No Known Activations