© 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. 9-RES-JB
    11. 18186
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action or making decisions to address various situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "take" in various contexts related to actions or measures

    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
    Cong
    -0.74
    tch
    -0.66
    atron
    -0.65
    Domin
    -0.61
    akin
    -0.60
    Bey
    -0.59
     accompanies
    -0.59
    itcher
    -0.59
    Haunted
    -0.59
     advertised
    -0.58
    POSITIVE LOGITS
     advantage
    1.11
     heed
    1.11
     precautions
    1.08
    aways
    1.02
     precaution
    0.99
     corrective
    0.96
     steps
    0.95
     action
    0.94
     aback
    0.93
     refuge
    0.92
    Activations Density 0.103%

    No Known Activations