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. 5-RES-JB
    6. 1732
    Prev
    Next
    INDEX
    Explanations

    university names

    oai_token-act-pair · gpt-3.5-turbo

    references to educational institutions and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nails
    -0.61
     Mehran
    -0.61
     sidx
    -0.57
    accompan
    -0.57
     lockout
    -0.53
     approving
    -0.52
    wagen
    -0.51
     toll
    -0.51
    monary
    -0.50
     showc
    -0.50
    POSITIVE LOGITS
    ibrary
    0.62
    IU
    0.57
    Ħ¢
    0.55
     plur
    0.54
    oxide
    0.54
    kus
    0.54
     dstg
    0.54
    styles
    0.52
    ISA
    0.51
    DN
    0.51
    Activations Density 1.426%

    No Known Activations