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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 5-RES-JB
    6. 12529
    Prev
    Next
    INDEX
    Explanations

    references to the software "Microsoft Office"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the "Office" software suite

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aye
    -0.85
    ulic
    -0.82
    anches
    -0.78
    hma
    -0.78
    ierrez
    -0.73
    nir
    -0.71
    vous
    -0.70
    onso
    -0.69
    ivals
    -0.69
    bley
    -0.69
    POSITIVE LOGITS
     365
    1.16
    365
    0.87
    mar
    0.72
    sworth
    0.71
     suite
    0.70
     Sphere
    0.69
     XP
    0.68
     Libre
    0.65
     xml
    0.65
    herent
    0.64
    Activations Density 0.025%

    No Known Activations