© 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. 12845
    Prev
    Next
    INDEX
    Explanations

    words associated with closely or near correlation or scrutiny

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a close association or scrutiny between subjects

    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
    inished
    -0.71
    iddler
    -0.67
    anish
    -0.62
    boat
    -0.61
     Ending
    -0.61
     saving
    -0.61
    laughter
    -0.60
     endings
    -0.60
     Offense
    -0.59
     Added
    -0.59
    POSITIVE LOGITS
     closely
    3.73
     carefully
    1.80
     intimately
    1.77
     tightly
    1.76
     thoroughly
    1.39
     extensively
    1.39
     faithfully
    1.36
     strongly
    1.34
     deeply
    1.33
     diligently
    1.32
    Activations Density 0.011%

    No Known Activations