© 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. 10-RES-JB
    11. 3331
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the start or initiation of an action or process

    oai_token-act-pair · gpt-3.5-turbo

    calls to action or invitations to engage in a task

    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
    iership
    -0.72
    ires
    -0.65
    lied
    -0.65
    amiya
    -0.62
    ELD
    -0.61
     veins
    -0.61
    KO
    -0.61
    elson
    -0.60
     externalToEVAOnly
    -0.59
    rays
    -0.58
    POSITIVE LOGITS
     ourselves
    1.19
     recap
    0.77
    eeee
    0.75
     briefly
    0.72
    reality
    0.71
     facts
    0.70
     pretend
    0.69
     hindsight
    0.69
     analogy
    0.69
     our
    0.69
    Activations Density 0.116%

    No Known Activations