© 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. 9-RES-JB
    11. 2742
    Prev
    Next
    INDEX
    Explanations

    years or time periods, particularly those related to the early decades of a century

    oai_token-act-pair · gpt-3.5-turbo

    references to early time periods or decades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avorite
    -0.77
    IDA
    -0.71
    sbm
    -0.68
    edIn
    -0.64
    NetMessage
    -0.63
    Compat
    -0.63
    Reviewer
    -0.62
    Dom
    -0.62
     Edited
    -0.61
    oppable
    -0.60
    POSITIVE LOGITS
     1990
    1.16
    ixties
    1.15
     1980
    1.11
     1970
    1.08
     twenties
    1.07
     stages
    1.04
     1960
    1.02
     aftermath
    0.99
     2000
    0.99
     1950
    0.91
    Activations Density 0.071%

    No Known Activations