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. 22478
    Prev
    Next
    INDEX
    Explanations

    phrases related to quantities or levels

    oai_token-act-pair · gpt-3.5-turbo

    quantitative descriptions related to amounts or levels

    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
    ©¶æ
    -0.71
    ĻĤ
    -0.68
    rums
    -0.57
    rones
    -0.55
     annex
    -0.52
     Skies
    -0.52
     Revision
    -0.51
    byter
    -0.50
    alter
    -0.50
    hemat
    -0.50
    POSITIVE LOGITS
     of
    1.30
    Of
    0.97
     thereof
    0.92
     OF
    0.90
    of
    0.88
     Of
    0.87
     amount
    0.81
    OF
    0.75
    pour
    0.67
    scl
    0.65
    Activations Density 0.237%

    No Known Activations