© 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. 2-RES-JB
    11. 12405
    Prev
    Next
    INDEX
    Explanations

    dates written in the format month/day/year with significant variation in date formats

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thous
    -0.72
    agna
    -0.72
     tremend
    -0.69
     fateful
    -0.68
     nomine
    -0.66
    iami
    -0.65
     practition
    -0.65
    paio
    -0.65
     Jobs
    -0.64
     bunny
    -0.63
    POSITIVE LOGITS
    88
    0.89
    657
    0.87
    708
    0.87
    665
    0.85
    806
    0.85
    008
    0.84
    307
    0.84
    245
    0.84
    66
    0.84
    646
    0.84
    Activations Density 0.165%

    No Known Activations