© 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. 10-RES-JB
    11. 8095
    Prev
    Next
    INDEX
    Explanations

    terms related to technology, such as "CPU cooler" and "e-book"

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to various subjects and concepts in technology, literature, and economics

    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
    nces
    -1.02
    aughs
    -0.92
     pillars
    -0.86
    iths
    -0.82
    bats
    -0.81
    awatts
    -0.79
     Horses
    -0.79
    atives
    -0.79
     iPads
    -0.79
     avenues
    -0.79
    POSITIVE LOGITS
     depends
    0.90
     consists
    0.89
    uble
    0.88
     cannot
    0.85
     consisting
    0.84
    herer
    0.83
     lover
    0.82
     ordinarily
    0.81
     requires
    0.81
    worker
    0.81
    Activations Density 0.381%

    No Known Activations