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. 2-RES-JB
    6. 24441
    Prev
    Next
    INDEX
    Explanations

    references to touchscreen technology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to touchscreens and interactions with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rams
    -0.91
    ilon
    -0.91
    uates
    -0.90
    olon
    -0.89
    uating
    -0.88
    uated
    -0.86
    inet
    -0.83
    liction
    -0.82
    choes
    -0.80
    ylon
    -0.80
    POSITIVE LOGITS
    STEM
    0.64
    ï¸ı
    0.63
    Tang
    0.63
     Swanson
    0.61
    WER
    0.61
     gesture
    0.61
    ï¸
    0.61
     McCl
    0.60
     Stephenson
    0.60
     Brewers
    0.60
    Activations Density 0.029%

    No Known Activations