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. 8-RES-JB
    6. 3802
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software updates and management

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technology and event management

    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
    é¾įå
    -0.84
    æ©
    -0.75
    âĹ¼
    -0.73
    ãģĦ
    -0.70
    çͰ
    -0.69
    Ire
    -0.68
    æĢ
    -0.66
    ãģį
    -0.66
    acly
    -0.66
    bledon
    -0.64
    POSITIVE LOGITS
    naire
    0.67
    ↵↵
    0.62
     heats
    0.59
    ifies
    0.59
     welcomes
    0.59
    Joined
    0.59
    undrum
    0.58
    ↵
    0.57
     exploded
    0.57
    malink
    0.56
    Activations Density 0.462%

    No Known Activations