© 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. 1-RES-JB
    11. 16367
    Prev
    Next
    INDEX
    Explanations

    dates in the format of year followed by numerical month with the highest activation on 2011

    oai_token-act-pair · gpt-3.5-turbo

    specific years or dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rath
    -0.80
     furious
    -0.72
    VERTISEMENT
    -0.71
     staggering
    -0.68
    imb
    -0.67
     lifelong
    -0.67
     paddle
    -0.65
     cheek
    -0.65
     fer
    -0.65
     quarter
    -0.65
    POSITIVE LOGITS
    theless
    1.34
    terday
    1.19
    DragonMagazine
    1.15
    odore
    0.97
    tenance
    0.95
    1984
    0.91
    2014
    0.90
    2001
    0.90
    romeda
    0.87
    1981
    0.86
    Activations Density 0.050%

    No Known Activations