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. 4-RES-JB
    6. 12763
    Prev
    Next
    INDEX
    Explanations

    mentions of physical harm or destruction by fire

    oai_token-act-pair · gpt-3.5-turbo

    references to fire, burning, and related injuries or destruction

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

    No Comments

    Negative Logits
    onsense
    -0.75
    ournal
    -0.74
     reluct
    -0.71
    awaru
    -0.69
    egal
    -0.68
    udeau
    -0.67
    ensical
    -0.66
    alian
    -0.66
    ortun
    -0.66
    remlin
    -0.65
    POSITIVE LOGITS
     burning
    1.14
     burn
    1.12
    ished
    1.04
     burns
    1.04
    ishing
    1.01
     hotter
    0.99
    burning
    0.98
     burned
    0.95
    ishes
    0.89
     burner
    0.86
    Activations Density 0.018%

    No Known Activations