© 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. 3-RES-JB
    11. 7251
    Prev
    Next
    INDEX
    Explanations

    specific years related to data or events

    oai_token-act-pair · gpt-3.5-turbo

    years, particularly focusing on the years 2007 and 2008

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ancest
    -0.74
    akin
    -0.73
     lawy
    -0.69
     limb
    -0.67
    plom
    -0.63
     unw
    -0.63
     polish
    -0.62
    ¤
    -0.62
    ¶æ
    -0.61
    warts
    -0.61
    POSITIVE LOGITS
    å¹
    0.87
    INESS
    0.74
    lishes
    0.74
     onwards
    0.70
    -'
    0.69
    lins
    0.68
    ilton
    0.68
    20439
    0.67
    lished
    0.65
    arella
    0.65
    Activations Density 0.020%

    No Known Activations