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. 0-RES-JB
    6. 3610
    Prev
    Next
    INDEX
    Explanations

    terms related to guns and disarmament

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to firearms and disarmament

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ethiop
    -0.77
     Ethiopian
    -0.71
     parasitic
    -0.70
     blogging
    -0.67
    paces
    -0.67
     IPM
    -0.65
    íķ
    -0.64
     paras
    -0.64
    atari
    -0.64
    bps
    -0.64
    POSITIVE LOGITS
    Gun
    2.91
     Guns
    2.79
     Firearms
    2.54
     Gun
    2.31
     Heller
    2.07
     GUN
    2.06
     gun
    2.05
    guns
    1.92
    gun
    1.91
     Arms
    1.84
    Activations Density 0.037%

    No Known Activations