© 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. 0-RES-JB
    11. 1231
    Prev
    Next
    INDEX
    Explanations

    words related to chemical compounds

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "ron" in various contexts

    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
     apart
    -0.68
     mosqu
    -0.66
     entangled
    -0.63
     diffuse
    -0.63
     versa
    -0.63
     victimized
    -0.61
     adolesc
    -0.61
     Afgh
    -0.59
     %%
    -0.59
     fragile
    -0.58
    POSITIVE LOGITS
    ron
    4.56
    rons
    2.82
    RON
    2.43
    ronic
    1.90
    rone
    1.68
    rones
    1.47
    ronics
    1.41
    ros
    1.39
    rom
    1.37
    ront
    1.36
    Activations Density 0.013%

    No Known Activations