© 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. 4875
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "egg" and variations in different contexts, not specifically looking for information related to eggs

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "gg" in various contexts

    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
     essence
    -0.70
     resolving
    -0.70
     resolve
    -0.69
     bearer
    -0.67
     chronic
    -0.63
     Spurs
    -0.63
     paralyzed
    -0.62
     NHS
    -0.62
     Hiroshima
    -0.61
     accumulated
    -0.61
    POSITIVE LOGITS
    gg
    1.25
    avin
    1.08
    raft
    1.02
    reen
    0.98
    alos
    0.97
    hetti
    0.96
    hetto
    0.94
    arette
    0.93
    ernaut
    0.90
    illet
    0.90
    Activations Density 0.008%

    No Known Activations