© 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. 10231
    Prev
    Next
    INDEX
    Explanations

    words related to ingredients or components

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with essential components and ingredients 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
    paces
    -1.23
    avers
    -1.17
    hips
    -1.14
    pace
    -1.08
    peed
    -1.06
    cale
    -1.04
    creen
    -1.04
    poons
    -1.01
    hops
    -0.98
    omething
    -0.95
    POSITIVE LOGITS
     count
    0.68
    mented
    0.65
     fisher
    0.64
    iously
    0.64
     mechanic
    0.61
    ment
    0.61
     trait
    0.60
     witness
    0.60
     component
    0.60
    Lie
    0.59
    Activations Density 0.028%

    No Known Activations