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. 17351
    Prev
    Next
    INDEX
    Explanations

    dates associated with the month of November

    oai_token-act-pair · gpt-3.5-turbo

    references to the month of November

    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
    xual
    -0.69
    enos
    -0.65
    ilic
    -0.62
    Static
    -0.61
     descendants
    -0.60
    ileged
    -0.60
    iko
    -0.59
    ree
    -0.59
    ular
    -0.59
     glances
    -0.58
    POSITIVE LOGITS
     November
    3.25
     December
    2.61
    November
    2.60
     October
    2.59
     September
    2.48
     January
    2.44
     February
    2.40
     July
    2.31
     August
    2.27
    October
    2.20
    Activations Density 0.011%

    No Known Activations