© 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. 16289
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "lifeline."

    oai_token-act-pair · gpt-3.5-turbo

    references to "life" and its stages or aspects

    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
     Monstrous
    -0.80
     Forbidden
    -0.75
     disagree
    -0.67
     Franks
    -0.65
     Pound
    -0.65
     Cardinal
    -0.65
     Taste
    -0.65
     Hide
    -0.61
     Dominion
    -0.61
    Ô
    -0.60
    POSITIVE LOGITS
    ecycle
    1.46
    etimes
    1.40
    elong
    1.25
    elines
    1.19
    eline
    1.12
    estone
    1.09
    ework
    1.08
    estones
    1.07
    lif
    1.03
    etime
    1.02
    Activations Density 0.006%

    No Known Activations