© 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. 4-RES-JB
    11. 828
    Prev
    Next
    INDEX
    Explanations

    action verbs related to digital tasks or functionalities

    oai_token-act-pair · gpt-3.5-turbo

    verbs and actions related to digital interactions and data manipulation

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

    No Comments

    Negative Logits
    fell
    -0.63
    soDeliveryDate
    -0.62
    egal
    -0.59
    Tonight
    -0.57
    being
    -0.54
    eq
    -0.54
    lihood
    -0.54
    usp
    -0.53
    Connector
    -0.53
    pmwiki
    -0.53
    POSITIVE LOGITS
     copies
    0.67
    ulate
    0.66
    matically
    0.66
     yourself
    0.61
     oneself
    0.61
     duplicate
    0.60
    ibly
    0.60
    untarily
    0.59
     manually
    0.59
    rogram
    0.57
    Activations Density 0.596%

    No Known Activations