© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 16708
    Prev
    Next
    INDEX
    Explanations

    days of the week

    oai_token-act-pair · gpt-3.5-turbo

    days of the week and their related 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
     Chronicle
    -0.71
     :=
    -0.69
    iframe
    -0.68
    gery
    -0.68
     quo
    -0.66
     Tsukuyomi
    -0.65
    eer
    -0.64
    ggle
    -0.63
     Mos
    -0.63
    Pros
    -0.63
    POSITIVE LOGITS
     afternoon
    0.96
     morning
    0.94
     evening
    0.92
     night
    0.90
     embold
    0.70
     NIGHT
    0.68
     honoring
    0.67
    night
    0.66
     accusing
    0.63
     outlining
    0.61
    Activations Density 0.127%

    No Known Activations