© 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. 0-RES-JB
    11. 20306
    Prev
    Next
    INDEX
    Explanations

    references to honey

    oai_token-act-pair · gpt-3.5-turbo

    references to honey

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocations
    -0.82
     Shogun
    -0.75
    agonist
    -0.72
     Samurai
    -0.71
    agonists
    -0.71
    gression
    -0.69
    Station
    -0.69
     Torch
    -0.68
     Races
    -0.67
     Sinclair
    -0.65
    POSITIVE LOGITS
     honey
    3.75
     Honey
    2.52
     bees
    1.74
     bee
    1.57
     Bees
    1.44
    oney
    1.27
     hive
    1.26
    bees
    1.26
     pollen
    1.23
     jelly
    1.20
    Activations Density 0.017%

    No Known Activations