© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 10416
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to research and publications

    oai_token-act-pair · gpt-3.5-turbo

    periods or punctuation at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gunfire
    -0.75
     booted
    -0.74
     curtains
    -0.71
     shaving
    -0.69
     forwarding
    -0.68
     shorth
    -0.67
     bets
    -0.67
     clock
    -0.67
     tipped
    -0.66
     chopping
    -0.65
    POSITIVE LOGITS
     Retrieved
    1.40
     Biol
    1.10
     PLoS
    1.10
     Proceedings
    1.07
     Neuroscience
    1.01
     Studies
    0.97
     Clin
    0.97
     Accessed
    0.94
     Transactions
    0.94
     Methods
    0.93
    Activations Density 0.171%

    No Known Activations