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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6-RES-JB
    6. 3241
    Prev
    Next
    INDEX
    Explanations

    terms related to business and economics

    oai_token-act-pair · gpt-3.5-turbo

    topics related to business economics and industry-related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    drop
    -0.86
     coerc
    -0.79
    othal
    -0.78
    xual
    -0.77
    arching
    -0.73
    Ö¼
    -0.73
    ayn
    -0.73
    emonic
    -0.70
     subp
    -0.69
    ferred
    -0.69
    POSITIVE LOGITS
     Insider
    0.69
    ERY
    0.65
     headquartered
    0.64
    INESS
    0.64
     Brune
    0.63
    Activity
    0.63
    steen
    0.63
     Sold
    0.62
     Bundy
    0.62
    ãĤ¼ãĤ¦ãĤ¹
    0.61
    Activations Density 0.155%

    No Known Activations