© 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. 1-RES-JB
    11. 14400
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Lif"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "life" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĶ°
    -0.68
     Saban
    -0.66
     revisions
    -0.66
     disagree
    -0.65
     Forbidden
    -0.64
     Shepherd
    -0.63
     Dominion
    -0.63
     Hide
    -0.61
     Firm
    -0.60
     Gillespie
    -0.60
    POSITIVE LOGITS
    ecycle
    1.30
    lif
    1.27
    etimes
    1.23
    etime
    1.22
    elong
    1.18
    etooth
    1.12
     Lif
    1.12
    ework
    1.08
    thood
    1.06
    estone
    1.02
    Activations Density 0.004%

    No Known Activations