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. 10-RES-JB
    6. 17145
    Prev
    Next
    INDEX
    Explanations

    version numbers in a specific format, such as "4.X.X"

    oai_token-act-pair · gpt-3.5-turbo

    phrases or references related to Android versioning and numerical identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     showc
    -0.69
    cius
    -0.69
    heit
    -0.66
     Howe
    -0.62
     glances
    -0.62
     Dirk
    -0.60
     Whitman
    -0.57
    anchester
    -0.56
    erella
    -0.56
     dialogue
    -0.56
    POSITIVE LOGITS
    fif
    0.93
    wheel
    0.80
    square
    0.76
    izons
    0.75
    quad
    0.74
    legged
    0.73
    digit
    0.73
    teen
    0.72
    ouk
    0.72
    teenth
    0.71
    Activations Density 0.070%

    No Known Activations