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

    Neuronpedia

    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. 8-RES-JB
    11. 3358
    Prev
    Next
    INDEX
    Explanations

    organic chemical compounds related to specific substitutions and chemical groups

    oai_token-act-pair · gpt-3.5-turbo

    chemical compounds, specifically those containing methyl and hydrogen

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irtual
    -0.80
    ieri
    -0.77
    istas
    -0.72
    ista
    -0.71
     Gunn
    -0.68
     Mahar
    -0.67
     Upload
    -0.67
    llan
    -0.67
    Downloadha
    -0.66
     Dull
    -0.65
    POSITIVE LOGITS
    ation
    0.99
    ated
    0.96
     hydrogen
    0.91
    ãĤ©
    0.90
     methyl
    0.86
    ethyl
    0.84
    oxy
    0.84
    aline
    0.83
    hyd
    0.78
    amic
    0.77
    Activations Density 0.039%

    No Known Activations