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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 14888
    Prev
    Next
    INDEX
    Explanations

    references to published articles in newspapers and journals

    oai_token-act-pair · gpt-3.5-turbo

    references to articles published in notable periodicals, particularly mentioning "the" followed by a publication name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transporting
    -0.75
    strap
    -0.74
     travers
    -0.73
    aji
    -0.73
     experimented
    -0.72
     breathing
    -0.70
     servicing
    -0.70
     extracting
    -0.69
     regulates
    -0.67
     experimenting
    -0.66
    POSITIVE LOGITS
     latter
    0.95
     latest
    0.93
     aforementioned
    0.93
    Journal
    0.88
     journal
    0.85
     Chronicle
    0.85
     Journal
    0.83
     Observer
    0.83
     press
    0.82
     National
    0.82
    Activations Density 0.522%

    No Known Activations