© 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. 8599
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Corn" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to corn and related terms

    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
    -0.84
    ufact
    -0.71
    ãģ®æ
    -0.66
    uyomi
    -0.64
    ħĭ
    -0.64
     livest
    -0.63
    CRIP
    -0.61
    irements
    -0.61
    earable
    -0.60
    allery
    -0.59
    POSITIVE LOGITS
    elia
    1.00
     Corn
    0.99
    Corn
    0.97
    flower
    0.94
    nect
    0.90
    iard
    0.85
    rigan
    0.83
    fe
    0.83
    bread
    0.83
    borough
    0.82
    Activations Density 0.004%

    No Known Activations