© 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. 4248
    Prev
    Next
    INDEX
    Explanations

    phrases related to policy and socio-economic issues, such as minimum wage, public education, and taxes

    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
    involved
    -0.69
    cture
    -0.60
    cific
    -0.54
    endum
    -0.54
    minist
    -0.53
    neau
    -0.52
    iral
    -0.51
     insider
    -0.50
    ãĤ¨ãĥ«
    -0.50
    ersen
    -0.49
    POSITIVE LOGITS
     etc
    0.60
     and
    0.56
     (.
    0.55
    ĵĺ
    0.55
     mathemat
    0.53
     Gujar
    0.53
     (!
    0.52
    Ĥ¬
    0.51
    ,.
    0.49
    à¼
    0.49
    Activations Density 0.691%

    No Known Activations