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. 20155
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific names or terms, including 'Shak', 'Tup', 'Pist', 'Pastebin', 'Ez', and 'Stoke'

    oai_token-act-pair · gpt-3.5-turbo

    names and terms related to specific individuals and organizations

    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
     Fenrir
    -0.74
    HUD
    -0.71
     Hogan
    -0.68
     Mamm
    -0.66
     Labrador
    -0.65
    Aid
    -0.64
    SD
    -0.64
     rabbits
    -0.64
     Wolf
    -0.63
     Bucks
    -0.63
    POSITIVE LOGITS
    icket
    0.94
    orius
    0.90
    ridge
    0.88
     Pist
    0.86
    arers
    0.84
    gow
    0.82
    sov
    0.82
    ires
    0.82
    otle
    0.81
    daq
    0.81
    Activations Density 0.021%

    No Known Activations