Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 17317
    Prev
    Next
    INDEX
    Explanations

    chemical elements or compounds, particularly related to chlorination

    oai_token-act-pair · gpt-3.5-turbo

    references to chlorine and related chemical compounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.96
    EMS
    -0.96
    Tickets
    -0.73
     Mavericks
    -0.73
    Interstitial
    -0.71
    OPLE
    -0.70
    Commerce
    -0.70
     Akin
    -0.69
     Ticket
    -0.69
    llers
    -0.69
    POSITIVE LOGITS
     chlor
    1.12
     chlorine
    1.04
    inated
    1.03
    chlor
    0.93
     dioxide
    0.93
    orescent
    0.89
    inating
    0.87
    ination
    0.87
    hex
    0.84
     fluor
    0.84
    Activations Density 0.032%

    No Known Activations