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. 5-RES-JB
    6. 8352
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving functions and variables

    oai_token-act-pair · gpt-3.5-turbo

    mathematical symbols and functions in a formal context

    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
     destro
    -0.92
    ascus
    -0.83
    abwe
    -0.75
    terday
    -0.74
     Palestin
    -0.71
    Downloadha
    -0.71
     corrid
    -0.70
     Niet
    -0.68
     charm
    -0.68
     fencing
    -0.67
    POSITIVE LOGITS
    wcsstore
    1.14
    ŃĶ
    1.04
     {\
    1.03
    times
    1.00
    frac
    0.93
    display
    0.92
    root
    0.88
    relative
    0.88
    begin
    0.88
    \\\\\\\\\\\\\\\\
    0.86
    Activations Density 0.013%

    No Known Activations