© 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. 9-RES-JB
    11. 6863
    Prev
    Next
    INDEX
    Explanations

    phrases related to project and team management

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ittal
    -0.78
    ophers
    -0.71
    qt
    -0.71
    sylvania
    -0.70
    Proof
    -0.68
    yi
    -0.68
    prev
    -0.67
    çīĪ
    -0.67
    reek
    -0.66
    func
    -0.65
    POSITIVE LOGITS
     affairs
    0.98
     expectations
    0.90
    uate
    0.90
     finances
    0.84
     complexity
    0.80
     conflicts
    0.80
     risks
    0.77
     budgets
    0.74
     risk
    0.70
    orously
    0.70
    Activations Density 0.071%

    No Known Activations