© 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. 7-RES-JB
    11. 20858
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of a lifespan or life duration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to life and lifecycles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monstrous
    -0.77
     Pound
    -0.73
     Forbidden
    -0.69
     disagree
    -0.65
     Dominion
    -0.64
     Madness
    -0.64
     Hide
    -0.63
     penetrating
    -0.61
     Irving
    -0.61
     Awakening
    -0.61
    POSITIVE LOGITS
    ecycle
    1.51
    etimes
    1.41
    elong
    1.27
    eline
    1.21
    elines
    1.16
    ework
    1.15
    etime
    1.13
    etooth
    1.12
    estone
    1.11
    estyles
    1.06
    Activations Density 0.030%

    No Known Activations