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. 8718
    Prev
    Next
    INDEX
    Explanations

    programming code syntax related to variable assignment

    oai_token-act-pair · gpt-3.5-turbo

    equal signs and assignments in programming or mathematical contexts

    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
     offering
    -0.57
     affidav
    -0.55
     hon
    -0.55
     antiv
    -0.53
     nurs
    -0.53
    wolf
    -0.52
    yrinth
    -0.52
     comfort
    -0.52
     doubts
    -0.52
     timely
    -0.51
    POSITIVE LOGITS
     =
    3.31
     +=
    2.19
    =
    2.10
     -=
    2.00
    =$
    1.89
     :=
    1.86
    ="
    1.78
    ='
    1.77
    ={
    1.75
    =-
    1.74
    Activations Density 0.015%

    No Known Activations