© 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. 10-RES-JB
    11. 17271
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and related terms, specifically focusing on ethyl and phenyl groups

    oai_token-act-pair · gpt-3.5-turbo

    chemical compounds and their structural components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rehearsal
    -0.72
     quirks
    -0.69
     Gunn
    -0.68
     Jaw
    -0.64
     slicing
    -0.62
     Gateway
    -0.62
    FontSize
    -0.62
     manuals
    -0.61
     Gould
    -0.60
    UNCH
    -0.60
    POSITIVE LOGITS
    ethyl
    1.29
    chlor
    1.23
    methyl
    1.21
    aldehyde
    1.20
    phen
    1.19
    amphetamine
    1.17
    oxide
    1.16
    oxy
    1.16
    hyd
    1.15
    acet
    1.13
    Activations Density 0.121%

    No Known Activations