© 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. 2166
    Prev
    Next
    INDEX
    Explanations

    keywords related to training, specifically in the context of supervised learning and physical exercises

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of training

    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
    vous
    -0.92
    xus
    -0.75
    osi
    -0.72
     Nas
    -0.68
    bi
    -0.67
    lihood
    -0.64
    fr
    -0.64
    pard
    -0.64
    izon
    -0.64
    vasive
    -0.63
    POSITIVE LOGITS
     Peaks
    0.89
     regimen
    0.83
     workouts
    0.82
     mont
    0.80
     prowess
    0.78
    UFC
    0.75
     workout
    0.75
     exercises
    0.73
     recomm
    0.72
     sessions
    0.72
    Activations Density 0.015%

    No Known Activations