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. 3375
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and software development, particularly actions related to building and coding

    oai_token-act-pair · gpt-3.5-turbo

    references to the process of creating or constructing various projects

    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
    lain
    -0.70
    nee
    -0.70
    Ĥİ
    -0.69
    nton
    -0.69
    worn
    -0.68
    iatus
    -0.68
    few
    -0.68
    leave
    -0.66
    wait
    -0.66
    ennes
    -0.66
    POSITIVE LOGITS
     prototypes
    0.84
     specifications
    0.78
     cryptographic
    0.78
    CSS
    0.77
     builds
    0.76
    strap
    0.73
     batches
    0.73
     software
    0.72
     specs
    0.72
    raper
    0.72
    Activations Density 0.049%

    No Known Activations