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. 9-RES-JB
    6. 9457
    Prev
    Next
    INDEX
    Explanations

    comments or opinions related to various topics

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinions or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ".[
    -0.76
     fulfil
    -0.75
    ."[
    -0.73
    Delivery
    -0.72
     solicitor
    -0.71
     prost
    -0.70
    EH
    -0.70
    iless
    -0.69
     lawful
    -0.69
    Virgin
    -0.69
    POSITIVE LOGITS
     offseason
    1.23
     Playoff
    1.17
     Playoffs
    1.13
     ESPN
    1.12
     playoff
    1.11
     Belichick
    1.05
    ESPN
    1.05
     Prediction
    1.04
     preseason
    1.03
     Baseball
    0.99
    Activations Density 0.730%

    No Known Activations