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. 8835
    Prev
    Next
    INDEX
    Explanations

    words related to procedural matters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to procedures and processes

    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
     Bever
    -0.75
    idas
    -0.72
    Sales
    -0.68
    issan
    -0.68
    asus
    -0.66
     Brands
    -0.65
    Beer
    -0.65
     Owner
    -0.64
    anges
    -0.64
     Dor
    -0.64
    POSITIVE LOGITS
     procedural
    4.16
     Proced
    2.84
     proced
    2.64
     jurisd
    1.18
     budgetary
    1.09
     procedure
    1.04
     scripted
    1.03
     substantive
    1.03
     rog
    1.00
     procedures
    0.96
    Activations Density 0.018%

    No Known Activations