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. 12-RES-JB
    6. 14596
    Prev
    Next
    INDEX
    Explanations

    commands or steps in a software development process

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    occurrences of the letter 'B' or variations in its case

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     discipl
    -0.77
     innocence
    -0.74
     Bashar
    -0.71
     BART
    -0.65
     eligibility
    -0.64
     barb
    -0.63
     Russo
    -0.63
     Communist
    -0.63
     unle
    -0.62
     Barbar
    -0.62
    POSITIVE LOGITS
    undle
    1.43
    rows
    1.24
    inary
    1.21
    atch
    1.21
    inding
    1.19
    ugs
    1.18
    ounds
    1.17
    ounding
    1.16
    ooting
    1.16
    inder
    1.14
    Activations Density 0.047%

    No Known Activations