© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 16126
    Prev
    Next
    INDEX
    Explanations

    words related to chemistry, particularly hydrogen and its reactions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of hydrogen in various scientific contexts

    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
    ournal
    -0.80
    akening
    -0.73
    cham
    -0.69
     Clause
    -0.69
    awar
    -0.67
    biz
    -0.65
     Tale
    -0.65
    ctors
    -0.65
    akings
    -0.64
    ================================================================
    -0.64
    POSITIVE LOGITS
     sulf
    1.08
     chloride
    1.01
     sulph
    0.98
     hydrogen
    0.97
     cyan
    0.97
     refuel
    0.91
     atom
    0.87
    ated
    0.87
     dioxide
    0.87
    aline
    0.87
    Activations Density 0.028%

    No Known Activations