© 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. 9-RES-JB
    11. 5185
    Prev
    Next
    INDEX
    Explanations

    descriptions related to political events and activities

    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
    Todd
    -0.88
    Ohio
    -0.80
    Utah
    -0.78
     thru
    -0.76
     folks
    -0.76
     darn
    -0.74
     Trey
    -0.74
    Ted
    -0.73
     Amtrak
    -0.72
     Courtney
    -0.71
    POSITIVE LOGITS
     Azerbai
    1.04
     parliamentary
    0.99
     Syri
    0.99
    ÄŁ
    0.98
     parliament
    0.98
     Kazakh
    0.96
     Rouhani
    0.95
    ÅŁ
    0.92
     Bulgarian
    0.91
     Kham
    0.90
    Activations Density 1.981%

    No Known Activations