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. 3-RES-JB
    6. 18819
    Prev
    Next
    INDEX
    Explanations

    dates and days of the week mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific days of the week, particularly Thursdays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umbn
    -0.82
    respons
    -0.72
    igated
    -0.70
    onductor
    -0.69
    inctions
    -0.67
    ection
    -0.67
    ����
    -0.66
    agos
    -0.66
    rust
    -0.66
    este
    -0.66
    POSITIVE LOGITS
     nights
    1.15
     mornings
    1.14
     morning
    1.08
     afternoon
    1.00
     night
    0.99
     evenings
    0.99
     Night
    0.99
     NIGHT
    0.93
     evening
    0.92
    days
    0.91
    Activations Density 0.089%

    No Known Activations