© 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. 12-RES-JB
    11. 3697
    Prev
    Next
    INDEX
    Explanations

    financial and economic terms and concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to significant laws and amendments related to governance and society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢ
    -0.85
    ãĥ£
    -0.83
    Ô
    -0.79
    ãĤ¸
    -0.75
    à©
    -0.72
     âĢ
    -0.70
    ãĥı
    -0.70
    âľ
    -0.70
    âĺ
    -0.69
    âĿ
    -0.69
    POSITIVE LOGITS
     would
    1.33
     could
    1.21
     existed
    1.20
     was
    1.20
     wasn
    1.20
     wouldn
    1.20
     might
    1.19
     occurred
    1.15
     seemed
    1.14
     remains
    1.13
    Activations Density 0.857%

    No Known Activations