© 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. 20481
    Prev
    Next
    INDEX
    Explanations

    dates and periods of time

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" in various contexts, particularly in relation to time references

    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
    omever
    -0.79
    nav
    -0.72
    itiz
    -0.71
    bet
    -0.68
    xual
    -0.66
    chens
    -0.66
    arians
    -0.64
    bre
    -0.62
    orsi
    -0.62
    erers
    -0.62
    POSITIVE LOGITS
     1990
    1.63
     1980
    1.58
     1970
    1.55
     1960
    1.50
     1950
    1.43
     1930
    1.33
     1940
    1.28
    ixties
    1.26
     1920
    1.21
     late
    1.20
    Activations Density 0.180%

    No Known Activations