© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 1518
    Prev
    Next
    INDEX
    Explanations

    occurrences of phrases related to pick-up services or activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to "pick up" actions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issance
    -0.85
    ĸļ
    -0.72
    rency
    -0.70
    qus
    -0.70
    ãĥ´ãĤ¡
    -0.70
    yrinth
    -0.68
    naissance
    -0.67
    isance
    -0.66
    ãĥĨãĤ£
    -0.63
    eur
    -0.63
    POSITIVE LOGITS
    axe
    0.80
     grapes
    0.78
     strawberries
    0.73
     berries
    0.69
     noses
    0.66
    yip
    0.66
    une
    0.63
     Tiff
    0.62
    tle
    0.62
    picking
    0.60
    Activations Density 0.114%

    No Known Activations