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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 1842
    Prev
    Next
    INDEX
    Explanations

    dates in the format "Month Day" (e.g., "Feb 9")

    oai_token-act-pair · gpt-3.5-turbo

    dates, specifically the occurrences of "February 9th" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.75
    éĹĺ
    -0.72
     polish
    -0.65
     Flavoring
    -0.65
    Offline
    -0.65
    enegger
    -0.64
     juggling
    -0.64
    Ø©
    -0.61
     wand
    -0.61
     parap
    -0.60
    POSITIVE LOGITS
    uary
    1.12
    ice
    1.02
    nd
    0.99
    vier
    0.91
    isco
    0.89
    bris
    0.87
    ipers
    0.87
    itor
    0.86
    itals
    0.85
    ital
    0.84
    Activations Density 0.006%

    No Known Activations