© 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. 3-RES-JB
    11. 23505
    Prev
    Next
    INDEX
    Explanations

    words that are commonly used or referred to

    oai_token-act-pair · gpt-3.5-turbo

    references to commonly accepted or frequently used concepts and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÄŁ
    -0.70
     Gareth
    -0.68
    anmar
    -0.67
    gur
    -0.67
     Fury
    -0.66
    him
    -0.63
    andra
    -0.63
     Majesty
    -0.63
     Bagg
    -0.62
    shi
    -0.61
    POSITIVE LOGITS
    entimes
    1.02
     encountered
    0.94
     abbrevi
    0.92
    Used
    0.88
     referred
    0.86
     regarded
    0.85
     known
    0.84
     identifiable
    0.82
     Asked
    0.82
     employed
    0.81
    Activations Density 0.012%

    No Known Activations