© 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 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. 10-RES-JB
    11. 3366
    Prev
    Next
    INDEX
    Explanations

    quotes and statements made by people in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to people's names and their roles or positions in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whilst
    -1.00
    ".[
    -0.91
     Whilst
    -0.84
    ONDON
    -0.79
    !".
    -0.78
    ÙĪ
    -0.77
    Ú
    -0.76
    Äĩ
    -0.75
    Ð
    -0.74
    Âł
    -0.74
    POSITIVE LOGITS
     spokeswoman
    1.12
     spokesman
    0.92
     attorney
    0.85
     supervisors
    0.84
     attorneys
    0.83
     Sgt
    0.82
     troopers
    0.80
     sheriff
    0.78
     Legislature
    0.78
     county
    0.77
    Activations Density 0.938%

    No Known Activations