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. 24114
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific location named "Cheshire"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Ches" and concepts related to "slate" and "canvas."

    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
     Grade
    -0.81
     Cult
    -0.81
     Rossi
    -0.79
     Ru
    -0.77
     RT
    -0.74
     Ring
    -0.74
    Bra
    -0.71
     Glenn
    -0.71
     Limbaugh
    -0.70
     Friedman
    -0.70
    POSITIVE LOGITS
     Ches
    2.22
     slate
    2.21
     canvas
    1.97
     palette
    1.39
     canv
    1.32
    apeake
    1.14
    buck
    1.02
     oy
    1.00
     bucket
    1.00
     contingency
    0.98
    Activations Density 0.046%

    No Known Activations