© 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. 6-RES-JB
    11. 21965
    Prev
    Next
    INDEX
    Explanations

    phrases related to additional items or information that enhance or complete something

    oai_token-act-pair · gpt-3.5-turbo

    references to dietary supplements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stem
    -0.75
    ĸ
    -0.73
    ¯
    -0.69
    fare
    -0.69
    akia
    -0.67
     loser
    -0.66
    ··
    -0.66
     Doodle
    -0.65
    ocene
    -0.64
    tags
    -0.63
    POSITIVE LOGITS
     supplements
    1.01
     supplement
    0.91
    aceutical
    0.89
    acebook
    0.88
    utical
    0.88
    ividual
    0.83
     creatine
    0.83
    ependent
    0.79
     supplementation
    0.78
    undown
    0.77
    Activations Density 0.032%

    No Known Activations