© 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. 11755
    Prev
    Next
    INDEX
    Explanations

    web browsers

    oai_token-act-pair · gpt-3.5-turbo

    references to web browsers

    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
    orian
    -0.80
     Lakes
    -0.74
    ioxide
    -0.70
    seeking
    -0.70
    Ñĭ
    -0.68
     Krish
    -0.67
    ŃĶ
    -0.64
    bucks
    -0.64
    ional
    -0.63
    qqa
    -0.63
    POSITIVE LOGITS
     toolbar
    0.99
     browsers
    0.94
     browser
    0.90
    browser
    0.88
     Browser
    0.79
     plugins
    0.79
    oad
    0.78
     interface
    0.76
     Firefox
    0.75
     plugin
    0.71
    Activations Density 0.018%

    No Known Activations