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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7799
    Prev
    Next
    INDEX
    Explanations

    dates in the format "Month Day"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the month "August" in various contexts

    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
     ancest
    -0.75
    >>>>>>>>
    -0.67
    itton
    -0.65
    cffff
    -0.65
     bom
    -0.64
    ggle
    -0.61
    ught
    -0.61
    kef
    -0.59
    ensical
    -0.58
    fect
    -0.58
    POSITIVE LOGITS
    mented
    1.17
    eenth
    1.15
    sburg
    0.99
    een
    0.96
     2018
    0.89
     Fourth
    0.84
     31
    0.84
     2017
    0.83
    mentation
    0.83
     2014
    0.82
    Activations Density 0.030%

    No Known Activations