© 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. 9-RES-JB
    11. 19778
    Prev
    Next
    INDEX
    Explanations

    verbs followed by the word "able" or "being able to" indicating a desire or capability to perform an action

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing the desire or ability to perform actions or tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parents
    -0.62
     Tradition
    -0.61
    afort
    -0.58
     Origin
    -0.57
     Bots
    -0.57
     Kendall
    -0.56
    ERN
    -0.54
    redo
    -0.54
    article
    -0.53
     Secrets
    -0.53
    POSITIVE LOGITS
    bodied
    1.17
    't
    0.84
    ioned
    0.80
     afford
    0.79
     to
    0.78
     bod
    0.77
     ta
    0.73
    ãĥīãĥ©
    0.71
     withstand
    0.70
    ny
    0.68
    Activations Density 0.050%

    No Known Activations