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. 8-RES-JB
    6. 4464
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "repe" followed by a number (such as "repe 10" or "repe 7")

    oai_token-act-pair · gpt-3.5-turbo

    terms related to regulations and repeals in legal and environmental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icals
    -0.79
    jamin
    -0.72
    ificial
    -0.72
    ãģ®ç
    -0.70
    itable
    -0.69
    ifice
    -0.67
     Oblivion
    -0.67
    é»Ĵ
    -0.65
    ication
    -0.65
    itarian
    -0.65
    POSITIVE LOGITS
    mite
    0.81
    pty
    0.74
    tti
    0.70
    BLE
    0.69
    airs
    0.69
    rers
    0.68
    UTH
    0.68
     cleaners
    0.65
    reen
    0.64
    mble
    0.64
    Activations Density 0.090%

    No Known Activations