© 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. 7-RES-JB
    11. 2007
    Prev
    Next
    INDEX
    Explanations

    sentences that end in periods

    oai_token-act-pair · gpt-3.5-turbo

    statements discussing programming or technical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    chair
    -0.66
     UNCLASSIFIED
    -0.64
    Amid
    -0.60
     Osama
    -0.60
     Fell
    -0.59
     Salman
    -0.58
    Political
    -0.58
     President
    -0.57
    Gov
    -0.57
     âĢİ
    -0.57
    POSITIVE LOGITS
     drawback
    0.91
    yip
    0.91
     simplified
    0.87
     simplest
    0.86
     simplicity
    0.84
     simpl
    0.83
     functionality
    0.83
     simplify
    0.82
     easiest
    0.81
     workflow
    0.80
    Activations Density 0.924%

    No Known Activations