© 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. 4-RES-JB
    11. 6040
    Prev
    Next
    INDEX
    Explanations

    mentions of specific days of the week, particularly Saturdays

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days of the week, particularly Saturday

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

    No Comments

    Negative Logits
    respons
    -0.90
    egal
    -0.87
    aeda
    -0.85
    ATOR
    -0.81
    vironment
    -0.79
    abet
    -0.78
    atem
    -0.77
    ographically
    -0.76
    ately
    -0.76
    arist
    -0.76
    POSITIVE LOGITS
     morning
    1.44
     afternoon
    1.41
     mornings
    1.37
     Night
    1.36
     night
    1.34
     evening
    1.25
     nights
    1.22
     Evening
    1.06
     Morning
    1.05
    Night
    1.02
    Activations Density 0.018%

    No Known Activations