© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 6162
    Prev
    Next
    INDEX
    Explanations

    words related to artillery or weapons

    oai_token-act-pair · gpt-3.5-turbo

    references to cannons or artillery-related terminology

    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
    EY
    -0.74
    Row
    -0.72
    Lisa
    -0.72
    actionDate
    -0.71
     Gram
    -0.71
    markets
    -0.68
    MIT
    -0.67
    Sym
    -0.67
    eps
    -0.65
    reen
    -0.65
    POSITIVE LOGITS
     cannon
    3.96
     cannons
    3.23
     Cannon
    2.54
     artillery
    1.57
     Cann
    1.47
     turret
    1.41
    annon
    1.38
     torped
    1.28
     projectiles
    1.27
     blaster
    1.26
    Activations Density 0.021%

    No Known Activations