© 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. 3-RES-JB
    11. 1746
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "fat" in text

    oai_token-act-pair · gpt-3.5-turbo

    references to dietary fat

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.72
     Schr
    -0.72
     Aerospace
    -0.71
    ECH
    -0.71
    yrinth
    -0.68
     Historic
    -0.68
     WARN
    -0.67
     Ascend
    -0.67
     McKenna
    -0.67
     Nieto
    -0.66
    POSITIVE LOGITS
    igue
    1.11
    rition
    0.95
    tailed
    0.93
    bag
    0.91
    hered
    0.90
    bike
    0.88
    bags
    0.86
     fat
    0.86
    ishes
    0.85
    fat
    0.84
    Activations Density 0.009%

    No Known Activations