© 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. 1-RES-JB
    11. 3220
    Prev
    Next
    INDEX
    Explanations

    references to chemical substances

    oai_token-act-pair · gpt-3.5-turbo

    references to chemical substances, particularly in the context of weapons

    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
     Wilde
    -0.83
     Ducks
    -0.81
     4090
    -0.80
    Scotland
    -0.80
     Remastered
    -0.80
     Coyotes
    -0.78
    rb
    -0.78
    shire
    -0.76
    ILLE
    -0.75
    yy
    -0.75
    POSITIVE LOGITS
     chemical
    1.36
     chemicals
    1.15
     compounds
    1.10
     substances
    1.08
     conflic
    1.03
     chlorine
    1.02
    chemical
    1.00
     makeup
    0.99
     oxide
    0.98
     additives
    0.96
    Activations Density 0.012%

    No Known Activations