© 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. 8-RES-JB
    11. 6981
    Prev
    Next
    INDEX
    Explanations

    phrases related to teamwork or collaboration

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions, specifically the word "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciples
    -0.79
    ":-
    -0.78
    ahime
    -0.74
    hart
    -0.72
    lex
    -0.69
    ributes
    -0.68
    gem
    -0.67
    igr
    -0.67
    eteen
    -0.66
    iji
    -0.66
    POSITIVE LOGITS
     rightfully
    1.15
     rightly
    1.11
     vice
    1.11
     indeed
    1.05
     possibly
    1.05
     hence
    1.05
     consequently
    1.03
     optionally
    1.01
    romeda
    1.01
     thereby
    0.98
    Activations Density 0.142%

    No Known Activations