Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 7173
    Prev
    Next
    INDEX
    Explanations

    words related to movement or steps

    oai_token-act-pair · gpt-3.5-turbo

    terms related to athletic performance and specific sports actions

    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
     Cra
    -0.68
     Ast
    -0.68
    plet
    -0.65
     Ele
    -0.64
     mushroom
    -0.64
     cannibal
    -0.64
     bir
    -0.63
    bol
    -0.62
    ingu
    -0.62
    aroo
    -0.62
    POSITIVE LOGITS
     stride
    3.39
     strides
    1.61
     blockers
    1.33
     Gamble
    1.27
    verson
    1.23
     scrimmage
    1.21
     blocker
    0.97
     Thiel
    0.92
     pads
    0.92
    yden
    0.90
    Activations Density 0.054%

    No Known Activations