© 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. 7-RES-JB
    11. 13531
    Prev
    Next
    INDEX
    Explanations

    words related to contaminants and toxic substances, particularly lead and mercury

    oai_token-act-pair · gpt-3.5-turbo

    references to toxic substances and environmental hazards, particularly lead and mercury

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    neys
    -0.80
    cffffcc
    -0.78
    hani
    -0.75
     NCT
    -0.70
     Kard
    -0.69
    Uber
    -0.68
    Sony
    -0.68
     Syri
    -0.68
     Fant
    -0.67
    Interview
    -0.67
    POSITIVE LOGITS
     oxide
    1.30
     dioxide
    1.26
     toxicity
    1.13
     chloride
    1.12
     concentrations
    1.10
     sulf
    1.08
     metabolites
    1.07
     compounds
    1.03
     sulph
    1.03
     concentration
    0.99
    Activations Density 0.118%

    No Known Activations