© 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. 1-RES-JB
    6. 9506
    Prev
    Next
    INDEX
    Explanations

    words related to explosives or explosive situations

    oai_token-act-pair · gpt-3.5-turbo

    references to explosive materials or devices

    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
    aird
    -0.83
    pai
    -0.76
    haps
    -0.73
    atche
    -0.73
    SEA
    -0.73
    cedented
    -0.73
    ordan
    -0.72
    ña
    -0.71
    Ĭ±
    -0.70
    aunder
    -0.70
    POSITIVE LOGITS
     explosive
    1.36
     incendiary
    0.99
     eru
    0.99
     bombshell
    0.94
     explosives
    0.90
     unbeliev
    0.86
     deton
    0.86
     decomp
    0.83
     Explosive
    0.83
     explosion
    0.82
    Activations Density 0.006%

    No Known Activations