© 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. 0-RES-JB
    11. 2880
    Prev
    Next
    INDEX
    Explanations

    references to the word "Days"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Days" and variations related to time spans or durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grapp
    -0.70
     lever
    -0.62
     above
    -0.61
     polymer
    -0.61
     subordinate
    -0.60
     ornament
    -0.59
     strat
    -0.59
     inferior
    -0.59
     synt
    -0.58
     weak
    -0.58
    POSITIVE LOGITS
     Days
    3.84
    Days
    2.67
     Hours
    1.95
     Months
    1.84
     Weeks
    1.71
    Hours
    1.63
     Years
    1.62
     days
    1.58
     Day
    1.56
     Nights
    1.55
    Activations Density 0.010%

    No Known Activations