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. 0-RES-JB
    6. 3427
    Prev
    Next
    INDEX
    Explanations

    the word "Stat" followed by either the number 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Stat" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hor
    -0.77
     loop
    -0.69
     homebrew
    -0.66
     Nare
    -0.66
    tones
    -0.66
     overload
    -0.65
     probing
    -0.64
    awa
    -0.63
     expose
    -0.62
     bends
    -0.62
    POSITIVE LOGITS
     Stat
    3.97
    Stat
    2.77
    stat
    2.12
     STAT
    1.88
     Statistical
    1.80
     stat
    1.74
    STAT
    1.61
     Stats
    1.59
     Statistics
    1.47
     statistic
    1.24
    Activations Density 0.012%

    No Known Activations