© 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. 11-RES-JB
    11. 6060
    Prev
    Next
    INDEX
    Explanations

    phrases involving communication and identity, particularly related to naming or defining something

    oai_token-act-pair · gpt-3.5-turbo

    references to identity and labels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    nown
    -0.75
    ashington
    -0.72
    idth
    -0.71
    continue
    -0.69
    angling
    -0.65
    few
    -0.64
    Pg
    -0.63
    hement
    -0.62
     ..........
    -0.61
    Need
    -0.61
    POSITIVE LOGITS
    ãĢİ
    0.81
     whatever
    0.77
     bluff
    0.75
     qu
    0.73
     lucky
    0.72
     anything
    0.70
     Nerd
    0.66
     something
    0.65
     "#
    0.64
     "@
    0.64
    Activations Density 0.058%

    No Known Activations