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. 8-RES-JB
    6. 23373
    Prev
    Next
    INDEX
    Explanations

    dates related to Fridays and events happening on Fridays

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the day "Friday" and its significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ership
    -0.98
    hip
    -0.80
    aeda
    -0.73
    itton
    -0.73
    atche
    -0.71
    estern
    -0.71
    ator
    -0.71
    istant
    -0.70
    ATOR
    -0.70
    arist
    -0.70
    POSITIVE LOGITS
     afternoon
    1.56
     morning
    1.53
     night
    1.42
     evening
    1.38
     mornings
    1.24
     Night
    1.17
     nights
    1.14
     evenings
    1.03
     prayers
    0.99
    night
    0.97
    Activations Density 0.050%

    No Known Activations