© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 13793
    Prev
    Next
    INDEX
    Explanations

    organic chemistry structures and drug-related terms

    oai_token-act-pair · gpt-3.5-turbo

    chemical compounds and their structural descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     misunderstand
    -0.87
     rehearsal
    -0.83
     regress
    -0.78
     bats
    -0.77
     sleeper
    -0.73
     raven
    -0.72
     quirks
    -0.68
     lounge
    -0.67
     Twins
    -0.67
     interviewing
    -0.65
    POSITIVE LOGITS
    methyl
    1.42
    ethyl
    1.29
    hyd
    1.24
    oxide
    1.24
    chlor
    1.22
    Hyd
    1.22
    cyclop
    1.21
    carb
    1.20
    phen
    1.19
    acet
    1.16
    Activations Density 0.125%

    No Known Activations