© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 9582
    Prev
    Next
    INDEX
    Explanations

    dates in the format month/day/year

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     brim
    -0.67
     thrill
    -0.65
     ado
    -0.62
     roar
    -0.62
     prey
    -0.62
     Tuls
    -0.62
     exagger
    -0.61
     concede
    -0.61
     rooting
    -0.60
     bribes
    -0.60
    POSITIVE LOGITS
    2015
    1.26
    2017
    1.24
    2016
    1.19
    2014
    1.19
    2012
    1.16
    2013
    1.16
    2001
    1.15
    2018
    1.15
    2006
    1.13
    2008
    1.11
    Activations Density 0.043%

    No Known Activations