© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20509
    Prev
    Next
    INDEX
    Explanations

    references to the word "walk" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "walk" and its variations

    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
     important
    -0.62
     Media
    -0.62
     Cyr
    -0.62
     Russia
    -0.62
     foc
    -0.61
     fluid
    -0.61
     ammunition
    -0.60
     settings
    -0.59
    ãĤ¦
    -0.58
     magnitude
    -0.58
    POSITIVE LOGITS
    walk
    4.65
    walking
    2.69
    walker
    2.45
    Walk
    2.25
    wal
    2.22
     Walk
    1.63
     walk
    1.44
     walks
    1.08
     stroll
    1.06
    park
    1.04
    Activations Density 0.007%

    No Known Activations