© 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. 5068
    Prev
    Next
    INDEX
    Explanations

    words related to different categories like food and beverages, law, maintenance, entertainment, and technology

    oai_token-act-pair · gpt-3.5-turbo

    specific brand names or key terms related to products or services

    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
     thereto
    -0.57
     âĢ¦"
    -0.52
     thereof
    -0.51
     trans
    -0.51
     encomp
    -0.51
     ..."
    -0.51
     unaccompanied
    -0.49
     respectively
    -0.48
     supra
    -0.48
     accompanied
    -0.48
    POSITIVE LOGITS
    roximately
    0.75
    ibliography
    0.71
    xiety
    0.71
    tymology
    0.70
    abases
    0.70
    ogether
    0.69
    vertising
    0.67
    notations
    0.66
    mosp
    0.65
    prisingly
    0.64
    Activations Density 0.647%

    No Known Activations