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. 4-RES-JB
    6. 8166
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to project management and work tasks

    oai_token-act-pair · gpt-3.5-turbo

    terms related to work, tasks, and project management

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

    No Comments

    Negative Logits
    é¾įå
    -0.78
    ãĥĥãĥī
    -0.76
    å§«
    -0.69
    ãĥ´
    -0.67
    çĭ
    -0.64
    ãĤ®
    -0.64
    ãģĦ
    -0.61
    ãģį
    -0.58
    çͰ
    -0.57
    dfx
    -0.57
    POSITIVE LOGITS
     heats
    0.47
    amp
    0.46
     Brett
    0.45
    ams
    0.45
    matically
    0.45
     scam
    0.44
    fecture
    0.44
     certification
    0.43
     IPM
    0.43
    regation
    0.43
    Activations Density 0.941%

    No Known Activations