© 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. 10-RES-JB
    11. 11507
    Prev
    Next
    INDEX
    Explanations

    quotations or spoken dialogue

    oai_token-act-pair · gpt-3.5-turbo

    quoted statements or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     favour
    -0.92
     favourable
    -0.89
     favoured
    -0.83
     authorised
    -0.77
     analys
    -0.73
     mediated
    -0.72
     criticised
    -0.70
     parliamentary
    -0.69
     imperialist
    -0.69
     Corbyn
    -0.68
    POSITIVE LOGITS
    Hopefully
    1.37
    Everybody
    1.31
    Obviously
    1.27
    Absolutely
    1.23
    Certainly
    1.21
     Hopefully
    1.15
    Basically
    1.13
    We
    1.11
    They
    1.10
    Kids
    1.08
    Activations Density 0.298%

    No Known Activations