© 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. 9-RES-JB
    11. 18169
    Prev
    Next
    INDEX
    Explanations

    dates in the format month, day, year, along with related events like arrests, shootings, and disappearances

    oai_token-act-pair · gpt-3.5-turbo

    dates and numerical references in chronological contexts

    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
    eton
    -0.68
     plat
    -0.63
    ¶
    -0.63
    ioned
    -0.61
     wasteland
    -0.60
    othe
    -0.59
    inctions
    -0.55
     trophies
    -0.55
    =-=-=-=-
    -0.53
     nar
    -0.53
    POSITIVE LOGITS
     2017
    1.47
     2014
    1.41
     2016
    1.37
     2015
    1.37
     2018
    1.37
     2013
    1.35
     2012
    1.31
     2011
    1.26
     2010
    1.22
     2019
    1.21
    Activations Density 0.091%

    No Known Activations