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. 1215
    Prev
    Next
    INDEX
    Explanations

    sections of text indicated by special characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of text formatted as notes or excerpts

    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
     confir
    -0.89
     tram
    -0.79
     probation
    -0.77
     cone
    -0.72
     capability
    -0.72
     county
    -0.72
     bloc
    -0.71
     fiat
    -0.70
     placement
    -0.70
     mandate
    -0.70
    POSITIVE LOGITS
    Introduction
    1.68
    Enlarge
    1.43
    Reviewed
    1.40
    Overview
    1.39
    THE
    1.37
    Born
    1.33
    Written
    1.33
    Advertisements
    1.32
    Throughout
    1.31
    Chapter
    1.31
    Activations Density 0.505%

    No Known Activations