© 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. 11-RES-JB
    11. 10270
    Prev
    Next
    INDEX
    Explanations

    verbs related to taking action or implementing a plan

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to actions taken or proposed in various contexts

    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
     Scouting
    -0.62
     REPL
    -0.54
    etermin
    -0.53
     Conquer
    -0.53
     Depot
    -0.52
     FAC
    -0.52
     Anything
    -0.51
    ))))
    -0.50
    itte
    -0.50
    itiveness
    -0.50
    POSITIVE LOGITS
     by
    1.25
     jointly
    1.04
     during
    0.95
     decades
    0.88
     earlier
    0.87
     annually
    0.85
     pursuant
    0.79
     centuries
    0.79
     BY
    0.77
    By
    0.77
    Activations Density 0.174%

    No Known Activations