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. 3-RES-JB
    6. 21843
    Prev
    Next
    INDEX
    Explanations

    government websites

    oai_token-act-pair · gpt-3.5-turbo

    references to government-related websites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Toast
    -0.79
     Blaze
    -0.70
    ordinary
    -0.68
     Crate
    -0.66
     virtues
    -0.66
     Mong
    -0.65
    Rust
    -0.64
     procedural
    -0.63
     Frie
    -0.62
    IENT
    -0.62
    POSITIVE LOGITS
    rolet
    0.91
    lisher
    0.89
    lishes
    0.89
    gov
    0.87
    edu
    0.83
    etsk
    0.83
    igation
    0.82
    hov
    0.80
    ulla
    0.79
    inces
    0.79
    Activations Density 0.005%

    No Known Activations