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. 4-RES-JB
    6. 19021
    Prev
    Next
    INDEX
    Explanations

    numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical values and statistics

    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
    displayText
    -0.71
    henko
    -0.68
     Collider
    -0.65
    HAM
    -0.63
    ULE
    -0.63
     Loans
    -0.61
    ARI
    -0.61
    Interstitial
    -0.61
    misc
    -0.60
     notor
    -0.59
    POSITIVE LOGITS
    eteen
    1.15
    Eight
    1.07
     thousand
    1.04
    irteen
    1.03
     Shades
    1.01
    teen
    0.99
    eight
    0.93
    ifty
    0.93
     Thousand
    0.91
     percent
    0.90
    Activations Density 0.010%

    No Known Activations