© 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. 8-RES-JB
    11. 22648
    Prev
    Next
    INDEX
    Explanations

    instances related to reconstruction or improvement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reconstruction or renewal

    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
    uchs
    -0.70
    cius
    -0.69
    cart
    -0.69
    rance
    -0.67
    Adv
    -0.67
    andra
    -0.66
    Sup
    -0.64
    andr
    -0.63
    hole
    -0.63
    istrate
    -0.63
    POSITIVE LOGITS
    ilitating
    0.92
     anew
    0.85
     rebuilding
    0.82
     rebuilt
    0.82
     rebuild
    0.78
     decaying
    0.75
     wounds
    0.75
    ilitation
    0.72
     intact
    0.72
     bridges
    0.71
    Activations Density 0.054%

    No Known Activations