© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4238
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific decades, particularly the 1980s

    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
    uden
    -0.78
    matically
    -0.73
    actor
    -0.71
    zag
    -0.66
    Hop
    -0.65
    acks
    -0.65
    axy
    -0.63
    hop
    -0.62
     hops
    -0.61
     hop
    -0.59
    POSITIVE LOGITS
    JV
    0.81
    80
    0.81
    IRC
    0.80
    oice
    0.76
    rpm
    0.73
    eenth
    0.73
    Ñĥ
    0.72
    itement
    0.71
    uously
    0.71
    SPA
    0.71
    Activations Density 0.118%

    No Known Activations