© 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. 0-RES-JB
    11. 19278
    Prev
    Next
    INDEX
    Explanations

    words related to nerves

    oai_token-act-pair · gpt-3.5-turbo

    references to nervous and muscular systems, as well as cellular structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trend
    -0.65
     similar
    -0.62
     revision
    -0.61
     UFO
    -0.61
    raine
    -0.60
     retrospective
    -0.60
    FA
    -0.60
    hip
    -0.59
    zel
    -0.58
    vis
    -0.58
    POSITIVE LOGITS
     nerves
    1.95
     atoms
    1.95
     muscles
    1.78
     neurons
    1.75
     electrons
    1.67
     chromosomes
    1.66
     proteins
    1.66
     arteries
    1.66
     ions
    1.64
     beads
    1.61
    Activations Density 0.064%

    No Known Activations