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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 6519
    Prev
    Next
    INDEX
    Explanations

    instances where locations are mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to significant topics or entities in a discussion

    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
    Aid
    -0.74
     Annotations
    -0.70
     Communism
    -0.67
    Scotland
    -0.66
     Travels
    -0.65
    esm
    -0.65
    itism
    -0.64
    arten
    -0.64
    links
    -0.64
     Chapters
    -0.64
    POSITIVE LOGITS
     same
    1.38
     aforementioned
    1.29
     latter
    1.20
    ses
    1.05
     entire
    1.04
     latest
    1.02
     opposite
    0.98
    oret
    0.94
     following
    0.92
     vast
    0.90
    Activations Density 0.099%

    No Known Activations