Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 11-RES-JB
    6. 3119
    Prev
    Next
    INDEX
    Explanations

    mentions of educational institutions, particularly colleges and schools

    oai_token-act-pair · gpt-3.5-turbo

    references to colleges and schools

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.64
     avail
    -0.62
    xon
    -0.60
     strokes
    -0.58
     appendix
    -0.58
    OME
    -0.58
     lord
    -0.57
     queen
    -0.56
     behav
    -0.56
    inventoryQuantity
    -0.56
    POSITIVE LOGITS
     Hospital
    0.93
     School
    0.84
     Chapel
    0.82
     Prep
    0.81
     Dublin
    0.79
     Publishers
    0.78
     Wilmington
    0.77
     Pom
    0.75
     Complex
    0.74
     Ltd
    0.74
    Activations Density 0.183%

    No Known Activations