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. 11754
    Prev
    Next
    INDEX
    Explanations

    terms related to firearms

    oai_token-act-pair · gpt-3.5-turbo

    words related to firearms and gun control issues

    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
     Stafford
    -0.72
     Schiff
    -0.69
     Sche
    -0.68
    ç«
    -0.67
     DAV
    -0.66
     Humph
    -0.66
     Carroll
    -0.66
     Hawth
    -0.65
     Harrington
    -0.62
     Kear
    -0.61
    POSITIVE LOGITS
    gun
    1.37
    ned
    1.15
    ners
    1.15
    guns
    1.15
    powder
    1.14
    rats
    1.03
    linger
    1.02
    hement
    1.00
    bats
    0.99
    igans
    0.99
    Activations Density 0.007%

    No Known Activations