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. 9-RES-JB
    6. 21673
    Prev
    Next
    INDEX
    Explanations

    words related to chemical elements, particularly focusing on the element "ium."

    oai_token-act-pair · gpt-3.5-turbo

    references to chemical elements and their compounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zee
    -0.84
    lier
    -0.79
    fare
    -0.78
    lihood
    -0.74
    orial
    -0.72
    hani
    -0.71
    soDeliveryDate
    -0.71
     CLSID
    -0.71
    LER
    -0.70
    terson
    -0.70
    POSITIVE LOGITS
     oxide
    1.67
     chloride
    1.45
     dioxide
    1.32
     alloy
    1.28
     iod
    1.25
     sulf
    1.23
     phosphate
    1.22
     ions
    1.21
     salts
    1.13
     nit
    1.12
    Activations Density 0.093%

    No Known Activations