© 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. 2834
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to names or titles

    oai_token-act-pair · gpt-3.5-turbo
    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
    ãĥĪ
    -0.86
    ctions
    -0.84
    ãĥīãĥ©
    -0.80
    kered
    -0.77
    ctive
    -0.75
    ivia
    -0.72
    ãĥ¬
    -0.70
    ãĥ©
    -0.69
    ctory
    -0.69
    ãĥ¤
    -0.68
    POSITIVE LOGITS
    robe
    2.01
    ens
    1.20
    ynski
    1.07
    wick
    0.98
    ell
    0.96
    een
    0.96
    er
    0.95
    age
    0.91
    lest
    0.90
    chester
    0.90
    Activations Density 0.043%

    No Known Activations