© 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. 20212
    Prev
    Next
    INDEX
    Explanations

    references to specific days of the week, especially Mondays

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Monday" and related contextual references

    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
    ript
    -1.03
    onductor
    -0.89
    iframe
    -0.84
    ordes
    -0.82
    ribe
    -0.81
    åĬ
    -0.76
    egal
    -0.75
    abet
    -0.72
    ategory
    -0.71
    respons
    -0.71
    POSITIVE LOGITS
     morning
    1.64
     afternoon
    1.60
     night
    1.53
     evening
    1.50
     mornings
    1.39
     Night
    1.32
    morning
    1.23
     nights
    1.20
     evenings
    1.09
     Morning
    1.00
    Activations Density 0.052%

    No Known Activations