© 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. 0-RES-JB
    11. 16681
    Prev
    Next
    INDEX
    Explanations

    the letters 'tl' appearing together

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to technology and software references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Levant
    -0.79
     Diver
    -0.70
     Archer
    -0.70
    ATIVE
    -0.66
     Hollow
    -0.66
     Grave
    -0.65
     Saber
    -0.64
     Aman
    -0.63
     Suit
    -0.62
     Galile
    -0.62
    POSITIVE LOGITS
    bt
    2.07
    pd
    2.06
    mc
    1.99
    nc
    1.93
    dp
    1.93
    bc
    1.93
    dm
    1.91
    dk
    1.90
    nb
    1.89
    tc
    1.88
    Activations Density 0.044%

    No Known Activations