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. 9280
    Prev
    Next
    INDEX
    Explanations

    phrases of contradiction or opposition

    oai_token-act-pair · gpt-3.5-turbo
    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
     Contains
    -0.74
    Released
    -0.67
    Reviewed
    -0.66
    Requires
    -0.65
    Synopsis
    -0.64
    PDF
    -0.61
    CLAIM
    -0.60
     Released
    -0.60
    Introduction
    -0.60
    ublished
    -0.59
    POSITIVE LOGITS
     yeah
    1.22
     secondly
    1.20
     everybody
    1.09
    entimes
    1.04
     somebody
    1.04
     nobody
    1.02
     we
    1.01
     I
    1.00
     luckily
    0.99
     [
    0.99
    Activations Density 0.303%

    No Known Activations