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. 3-RES-JB
    6. 7356
    Prev
    Next
    INDEX
    Explanations

    references to the version control system 'Git'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the version control system Git

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spr
    -0.72
    ammy
    -0.70
    mares
    -0.65
     Palestin
    -0.65
    FontSize
    -0.65
    eous
    -0.64
    ffield
    -0.63
    GHz
    -0.63
    eal
    -0.62
    ACP
    -0.62
    POSITIVE LOGITS
     repository
    0.83
     Git
    0.81
    mire
    0.80
     git
    0.78
     repositories
    0.77
    lab
    0.76
    yard
    0.76
    modules
    0.73
     stash
    0.70
    tags
    0.70
    Activations Density 0.009%

    No Known Activations