Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 10340
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or actions leading up to a significant moment

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a progression of events leading up to a specific time or event

    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
    azel
    -0.69
    avorite
    -0.66
    gans
    -0.66
     scapego
    -0.64
    Pers
    -0.62
    inen
    -0.61
    Filter
    -0.61
    aren
    -0.61
    mist
    -0.60
    matically
    -0.60
    POSITIVE LOGITS
    stage
    0.92
    stairs
    0.91
    actionDate
    0.84
    imester
    0.77
    wards
    0.75
    WARD
    0.74
     thereto
    0.69
     puberty
    0.69
    dating
    0.68
    phrine
    0.66
    Activations Density 0.030%

    No Known Activations