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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 4650
    Prev
    Next
    INDEX
    Explanations

    phrases related to starting or beginning

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Izan
    -0.73
    ividual
    -0.72
    nen
    -0.69
    ACTED
    -0.68
    cyclopedia
    -0.68
    enance
    -0.64
    clud
    -0.64
     Known
    -0.63
    chens
    -0.63
    yg
    -0.63
    POSITIVE LOGITS
     rocky
    1.00
     shaky
    0.80
     disappointing
    0.74
    oots
    0.73
     rough
    0.73
     slow
    0.72
     tails
    0.72
     rave
    0.71
     start
    0.70
     roaring
    0.68
    Activations Density 0.075%

    No Known Activations