© 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. 0-RES-JB
    11. 5370
    Prev
    Next
    INDEX
    Explanations

    keywords related to organic chemistry, specifically compounds containing "methyl" and "ethyl"

    oai_token-act-pair · gpt-3.5-turbo

    chemical compounds related to methylation 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 @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Glas
    -0.81
     Gree
    -0.80
     Garfield
    -0.78
     Griffin
    -0.77
     Lowry
    -0.77
    atche
    -0.74
    ailable
    -0.72
     Courier
    -0.68
    arts
    -0.68
     Jagu
    -0.67
    POSITIVE LOGITS
     methyl
    2.19
    YS
    1.80
    ethyl
    1.67
    Software
    1.59
    methyl
    1.47
    Sil
    1.30
    Phil
    1.28
     Liu
    1.13
     Dol
    1.08
    wcsstore
    1.00
    Activations Density 0.045%

    No Known Activations