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. 1-RES-JB
    6. 19841
    Prev
    Next
    INDEX
    Explanations

    words related to the Haskell programming language

    oai_token-act-pair · gpt-3.5-turbo

    references to the programming language Haskell and its associated components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IU
    -0.76
    unes
    -0.72
    uds
    -0.67
    cles
    -0.65
    illard
    -0.64
    ensor
    -0.64
     Rivals
    -0.63
    illa
    -0.63
     Cly
    -0.62
    rahim
    -0.62
    POSITIVE LOGITS
    kell
    1.25
     Haskell
    0.96
    querade
    0.77
     GHC
    0.73
    ollen
    0.71
     Prelude
    0.67
    istani
    0.65
    enstein
    0.64
    WAYS
    0.64
    herty
    0.63
    Activations Density 0.010%

    No Known Activations