© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 22339
    Prev
    Next
    INDEX
    Explanations

    verbs related to action

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "takes" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilk
    -0.63
    hift
    -0.62
    raq
    -0.62
    SHARE
    -0.61
    andal
    -0.57
    chell
    -0.56
    ãĥ¼
    -0.55
     academ
    -0.55
     Mann
    -0.53
    igham
    -0.53
    POSITIVE LOGITS
     takes
    2.95
     Takes
    1.93
     took
    1.78
     take
    1.61
     assumes
    1.61
     eats
    1.55
     pays
    1.51
     gets
    1.48
     consumes
    1.47
     starts
    1.46
    Activations Density 0.014%

    No Known Activations