© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 9393
    Prev
    Next
    INDEX
    Explanations

    the word "roll", especially in contexts related to various activities or names

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "roll"

    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
    ¿½
    -0.70
    rament
    -0.66
    apolis
    -0.64
    dylib
    -0.64
     Baptist
    -0.61
    cond
    -0.61
     Realms
    -0.60
     ray
    -0.59
     lux
    -0.59
    gdala
    -0.59
    POSITIVE LOGITS
    roll
    0.96
    rolling
    0.86
    nut
    0.85
    nuts
    0.85
    enaries
    0.81
    OUGH
    0.80
    ows
    0.79
    outing
    0.79
    owed
    0.78
    ocobo
    0.78
    Activations Density 0.004%

    No Known Activations