© 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. 10-RES-JB
    11. 23291
    Prev
    Next
    INDEX
    Explanations

    dates and specific days of the week

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of dates and related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Underworld
    -0.99
     TAG
    -0.87
     subscript
    -0.86
    tern
    -0.84
     Tub
    -0.82
    ubi
    -0.81
    alog
    -0.78
     Vert
    -0.78
    erent
    -0.78
     raven
    -0.77
    POSITIVE LOGITS
     May
    1.46
    May
    1.45
    Apr
    1.12
     Mayo
    1.07
    05
    1.03
     05
    1.03
     Maya
    1.02
     Apr
    1.01
     MAY
    0.98
     April
    0.96
    Activations Density 0.287%

    No Known Activations