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. 18881
    Prev
    Next
    INDEX
    Explanations

    terms related to education, specifically focusing on school institutions and activities

    oai_token-act-pair · gpt-3.5-turbo

    references to educational institutions and systems

    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
    £ı
    -0.81
    èĢħ
    -0.75
    ipolar
    -0.75
    redo
    -0.74
    STAR
    -0.73
    Balt
    -0.73
    achev
    -0.72
    åĬ
    -0.72
    etsk
    -0.72
    ãĥĥãĥĪ
    -0.71
    POSITIVE LOGITS
     Soup
    0.65
     clad
    0.63
     condol
    0.63
     Gardens
    0.59
     Trayvon
    0.59
     attendants
    0.58
     Kids
    0.58
     Shirley
    0.57
     Halls
    0.57
     newsletters
    0.57
    Activations Density 0.512%

    No Known Activations