© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 15167
    Prev
    Next
    INDEX
    Explanations

    phrases related to explosives or dangerous situations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of explosive devices or descriptions of explosive situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cedented
    -0.88
    aird
    -0.86
    SEA
    -0.78
    krit
    -0.77
    pai
    -0.77
    wright
    -0.77
    heit
    -0.76
    atche
    -0.75
    alian
    -0.75
    ournal
    -0.74
    POSITIVE LOGITS
     explosive
    1.09
     decomp
    0.89
     eru
    0.88
     incendiary
    0.85
     bursts
    0.78
     darts
    0.78
    onite
    0.77
     deton
    0.75
     explodes
    0.74
     flares
    0.73
    Activations Density 0.011%

    No Known Activations