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. 11934
    Prev
    Next
    INDEX
    Explanations

    documents or reports citing specific studies or research

    oai_token-act-pair · gpt-3.5-turbo

    references to reports or studies credited to various organizations or institutions

    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
    ãĤ¦ãĤ¹
    -0.98
    Interstitial
    -0.74
    usercontent
    -0.70
    ãĥİ
    -0.67
    photos
    -0.66
    Synopsis
    -0.65
    ukong
    -0.65
    Attempt
    -0.64
    reci
    -0.64
    ãĤ©
    -0.64
    POSITIVE LOGITS
     researchers
    1.00
     researcher
    0.96
     Pric
    0.95
     Physicians
    0.91
     Bloomberg
    0.90
     economists
    0.89
     consultancy
    0.89
     watchdog
    0.88
     academics
    0.88
     Amnesty
    0.86
    Activations Density 0.174%

    No Known Activations