© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 10151
    Prev
    Next
    INDEX
    Explanations

    words related to walking or movement on a specific surface, particularly emphasizing the act of 'treading'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to walking, movement, and physical pathways

    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
    ITIES
    -0.74
    oult
    -0.68
    gdala
    -0.65
     Kamp
    -0.65
    ARP
    -0.65
     deduction
    -0.60
    idal
    -0.60
    ulton
    -0.59
     fix
    -0.59
    ities
    -0.59
    POSITIVE LOGITS
     tread
    1.27
    cliffe
    1.00
    manship
    0.91
    wear
    0.83
    SourceFile
    0.80
    pants
    0.80
    shire
    0.78
    neck
    0.78
    leys
    0.78
    DragonMagazine
    0.77
    Activations Density 0.017%

    No Known Activations