© 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. 1-RES-JB
    11. 16839
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "corn"

    oai_token-act-pair · gpt-3.5-turbo

    references to corn and its various aspects or uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lumpur
    -0.75
     reperto
    -0.72
    llers
    -0.71
    deen
    -0.70
    */(
    -0.69
     newsp
    -0.68
     Stranger
    -0.68
     Shapiro
    -0.66
    gencies
    -0.66
     SetFontSize
    -0.65
    POSITIVE LOGITS
     corn
    1.22
    grain
    1.11
    Corn
    1.01
    corn
    1.01
    nect
    0.93
    flower
    0.93
     starch
    0.93
     syrup
    0.91
    otle
    0.89
    seed
    0.88
    Activations Density 0.007%

    No Known Activations