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. 7-RES-JB
    6. 5971
    Prev
    Next
    INDEX
    Explanations

    mentions of elite groups or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to elite groups or classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asca
    -0.83
    OUT
    -0.74
    acles
    -0.74
    TEXTURE
    -0.73
    alam
    -0.71
    DAY
    -0.71
    displayText
    -0.70
    atti
    -0.70
    NEY
    -0.69
    cone
    -0.69
    POSITIVE LOGITS
     Institution
    0.80
     elite
    0.76
    holm
    0.75
     cad
    0.72
     level
    0.71
     athlete
    0.70
     athletes
    0.70
     prepar
    0.69
     academy
    0.69
     classes
    0.68
    Activations Density 0.031%

    No Known Activations