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. 0-RES-JB
    6. 14308
    Prev
    Next
    INDEX
    Explanations

    names of elementary schools

    oai_token-act-pair · gpt-3.5-turbo

    references to elementary and kindergarten schools

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    plate
    -0.67
    Brand
    -0.65
    kered
    -0.61
    worn
    -0.60
     booked
    -0.60
    tracking
    -0.59
    VP
    -0.58
    plates
    -0.58
    frames
    -0.58
     CAM
    -0.58
    POSITIVE LOGITS
     Elementary
    3.59
     elementary
    3.23
     kindergarten
    2.01
     preschool
    1.86
     kinderg
    1.80
     classrooms
    1.37
    chool
    1.27
     teachers
    1.22
     educators
    1.20
     Kinder
    1.20
    Activations Density 0.021%

    No Known Activations