© 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. 10-RES-JB
    11. 2275
    Prev
    Next
    INDEX
    Explanations

    financial terms and quarterly reports related to finance and industries

    oai_token-act-pair · gpt-3.5-turbo

    financial reporting periods and quarterly metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     indo
    -0.75
     lawy
    -0.71
     glac
    -0.66
    umbn
    -0.65
     barr
    -0.64
     parap
    -0.61
     anat
    -0.61
     balk
    -0.60
     tyrann
    -0.59
    UGH
    -0.59
    POSITIVE LOGITS
     2015
    1.37
     2014
    1.36
     2017
    1.35
     2013
    1.32
     2016
    1.31
    2017
    1.30
    2014
    1.30
    2013
    1.29
     2018
    1.29
     2012
    1.27
    Activations Density 0.118%

    No Known Activations