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. 2-RES-JB
    6. 2671
    Prev
    Next
    INDEX
    Explanations

    references to bombers in various contexts, including suicide bombers, bomber aircraft, bomber jackets, and historical events involving bombers

    oai_token-act-pair · gpt-3.5-turbo

    references to bombers, particularly in contexts relating to danger or attacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Nev
    -0.87
    VID
    -0.84
    laus
    -0.83
    oint
    -0.79
    PE
    -0.74
    UTC
    -0.71
    Rest
    -0.71
    Ven
    -0.70
    ords
    -0.68
    Lot
    -0.68
    POSITIVE LOGITS
     bomber
    1.40
     bombers
    1.26
     Bomber
    1.02
     bombing
    1.00
     Bom
    0.96
     detonated
    0.82
     bombings
    0.79
     squadron
    0.76
    bsite
    0.74
     carrier
    0.74
    Activations Density 0.010%

    No Known Activations