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. 6-RES-JB
    6. 14159
    Prev
    Next
    INDEX
    Explanations

    numerical references to time periods, particularly the second half

    oai_token-act-pair · gpt-3.5-turbo

    references to "the second half" of a time period or event

    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
    RY
    -0.70
    pload
    -0.69
    Reviewed
    -0.68
    inates
    -0.68
    incinn
    -0.65
     confir
    -0.64
    ERT
    -0.63
    urat
    -0.63
    mercial
    -0.62
    lished
    -0.61
    POSITIVE LOGITS
    pipe
    0.86
    enium
    0.84
     hour
    0.69
    nings
    0.68
    heartedly
    0.67
     dozen
    0.66
    imester
    0.66
    ftime
    0.65
    kick
    0.65
     Engels
    0.64
    Activations Density 0.017%

    No Known Activations