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. 9-RES-JB
    6. 22241
    Prev
    Next
    INDEX
    Explanations

    dates written in a specific format: month, year, and parentheses around the day with varying activations for different occurrences

    oai_token-act-pair · gpt-3.5-turbo

    parentheses and their associated numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     centr
    -0.81
     compromised
    -0.71
     pastoral
    -0.66
     Pax
    -0.63
     Punk
    -0.62
     pitched
    -0.62
     Maced
    -0.61
     bipolar
    -0.61
     perspect
    -0.61
     polarized
    -0.60
    POSITIVE LOGITS
    24
    1.02
    28
    0.99
    13
    0.98
    16
    0.98
    33
    0.97
    15
    0.96
    14
    0.95
    12
    0.94
    39
    0.94
    17
    0.94
    Activations Density 0.107%

    No Known Activations