Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 22642
    Prev
    Next
    INDEX
    Explanations

    mentions of academic institutions or organizational structures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to academic institutions 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
    holes
    -0.75
     Galaxy
    -0.75
     Patel
    -0.74
     Send
    -0.68
    hole
    -0.64
     Valentine
    -0.64
     Mau
    -0.64
     PU
    -0.63
    RF
    -0.62
     Mew
    -0.62
    POSITIVE LOGITS
    edia
    0.97
    otrop
    0.92
    phe
    0.91
    onite
    0.91
    ICS
    0.91
    alog
    0.90
    cohol
    0.88
    ischer
    0.88
    ICAL
    0.88
    onyms
    0.87
    Activations Density 0.034%

    No Known Activations