© 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. 3136
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "lemon" with varying levels of emphasis and contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the words "lemon" and "lime."

    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
    Desc
    -0.79
    raints
    -0.74
    States
    -0.74
     Pension
    -0.74
    PsyNetMessage
    -0.72
    Platform
    -0.72
     Occupations
    -0.72
    issued
    -0.69
    Universal
    -0.69
    ollow
    -0.68
    POSITIVE LOGITS
     lemon
    1.10
     juice
    1.07
     fruits
    0.92
     Lemon
    0.92
    fruit
    0.91
     peel
    0.90
     Lime
    0.88
     juices
    0.85
     Tart
    0.84
     squee
    0.81
    Activations Density 0.007%

    No Known Activations