© 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. 6875
    Prev
    Next
    INDEX
    Explanations

    mentions of cast members in a film or TV show

    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
    DonaldTrump
    -0.72
    atten
    -0.68
     Accessed
    -0.67
    ufact
    -0.65
    Weapon
    -0.64
    Dom
    -0.62
    imon
    -0.61
    Requ
    -0.61
    ICO
    -0.60
     Pharma
    -0.59
    POSITIVE LOGITS
    members
    1.26
     members
    1.11
     mates
    1.10
    mates
    1.05
    aways
    1.05
     gathered
    0.98
     reunion
    0.93
     unanimously
    0.93
     consisted
    0.90
     assembled
    0.88
    Activations Density 0.253%

    No Known Activations