© 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. 0-RES-JB
    6. 12163
    Prev
    Next
    INDEX
    Explanations

    Instances of the word "walk"

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of walking

    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
     Salman
    -0.76
    encies
    -0.72
    reditary
    -0.72
    ãĤ´ãĥ³
    -0.71
    ative
    -0.71
    ymm
    -0.70
    afort
    -0.70
    ãĥķ
    -0.68
    XXX
    -0.67
    indal
    -0.66
    POSITIVE LOGITS
     walk
    3.56
     Walk
    2.38
     walks
    2.31
    Walk
    2.23
    walk
    2.17
     stroll
    2.12
     walking
    2.05
     walked
    1.82
     jog
    1.66
     crawl
    1.64
    Activations Density 0.009%

    No Known Activations