© 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 EvalsExportsinterp-engineNEWAPI 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. 2778
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "said," indicating reported speech or quotations

    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
    figure
    -0.70
    wed
    -0.62
     ÂŃ
    -0.61
    clad
    -0.60
    enburg
    -0.60
    pees
    -0.58
     inund
    -0.57
    eland
    -0.56
    anu
    -0.56
    izable
    -0.56
    POSITIVE LOGITS
     goodbye
    0.85
     hello
    0.83
    :
    0.82
    =\"
    0.81
    escription
    0.77
    .:
    0.74
    Hello
    0.74
     :
    0.72
    :-
    0.71
    :]
    0.69
    Activations Density 0.047%

    No Known Activations