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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 18431
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of the lifespan or duration of various objects or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to life and lifecycle concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pound
    -0.76
     Monstrous
    -0.69
     Forbidden
    -0.69
     prevailing
    -0.62
     Dominion
    -0.62
     disagree
    -0.61
     penetrating
    -0.59
     dressing
    -0.59
     Irving
    -0.59
     naming
    -0.58
    POSITIVE LOGITS
    ecycle
    1.64
    etimes
    1.50
    elong
    1.27
    elines
    1.25
    ework
    1.23
    etime
    1.19
    estone
    1.19
    eline
    1.18
    etooth
    1.15
    estones
    1.12
    Activations Density 0.028%

    No Known Activations