© 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. 0-RES-JB
    11. 6160
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for mentions of the compound methane

    oai_token-act-pair · gpt-3.5-turbo

    mentions of methane and its relevance in various contexts

    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
    Box
    -0.79
     Tai
    -0.78
    Roll
    -0.70
    ws
    -0.70
     Bul
    -0.68
    Bul
    -0.68
    cade
    -0.67
     Hung
    -0.67
     Brow
    -0.67
     Brit
    -0.66
    POSITIVE LOGITS
     methane
    3.71
     Meth
    1.83
     ammonia
    1.64
     ethanol
    1.28
     methamphetamine
    1.27
     fentanyl
    1.26
     mercury
    1.25
     biomass
    1.22
     ozone
    1.21
    entanyl
    1.20
    Activations Density 0.034%

    No Known Activations