© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-RES-JB
    11. 15593
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    references to actions or behaviors, particularly those signified by the word "act" and its variations

    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
    fortable
    -0.74
    hander
    -0.63
     Saga
    -0.60
    vae
    -0.59
    focus
    -0.59
    gaard
    -0.58
     Towers
    -0.58
     Gateway
    -0.58
    umbo
    -0.58
     pudding
    -0.57
    POSITIVE LOGITS
    uary
    1.45
    uated
    1.24
    ional
    1.22
    uation
    1.16
    ivism
    1.12
    uating
    1.11
    uate
    1.09
    ives
    1.07
    ual
    1.04
    uality
    1.02
    Activations Density 0.037%

    No Known Activations