© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 3493
    Prev
    Next
    INDEX
    Explanations

    words related to action or decision-making

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "go" and its variations used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emort
    -0.65
     XD
    -0.64
    Origin
    -0.61
    ificent
    -0.59
    emic
    -0.58
    olen
    -0.57
     (~
    -0.55
    season
    -0.55
    âķ
    -0.55
    oret
    -0.55
    POSITIVE LOGITS
    verning
    1.07
    aded
    0.93
     ahead
    0.91
    ggle
    0.88
     forward
    0.88
    vt
    0.88
     overboard
    0.88
    ading
    0.82
     toe
    0.82
    lems
    0.82
    Activations Density 0.075%

    No Known Activations