© 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. 0-RES-JB
    11. 9955
    Prev
    Next
    INDEX
    Explanations

    verbs related to intentions or plans

    oai_token-act-pair · gpt-3.5-turbo

    expressions of intention

    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
     peaks
    -0.63
     peak
    -0.58
     Diff
    -0.58
    toggle
    -0.55
     clicks
    -0.55
     rh
    -0.55
     Keane
    -0.54
     Tip
    -0.54
    pop
    -0.54
     quick
    -0.54
    POSITIVE LOGITS
     intend
    3.30
     intends
    2.66
     intending
    2.07
     intended
    1.73
     intention
    1.70
    intend
    1.46
     intentions
    1.44
     plans
    1.41
     plan
    1.37
     intent
    1.33
    Activations Density 0.009%

    No Known Activations