© 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. 11-RES-JB
    6. 1856
    Prev
    Next
    INDEX
    Explanations

    words related to exclusivity and promotions, such as "exclusive", "special", "tour", "release"

    oai_token-act-pair · gpt-3.5-turbo

    words with a specific focus on rating or evaluation

    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
    apters
    -0.73
    iced
    -0.71
    icing
    -0.69
    ices
    -0.68
    oter
    -0.68
    cill
    -0.66
    acity
    -0.66
    olulu
    -0.66
    unci
    -0.64
    atur
    -0.64
    POSITIVE LOGITS
    VILLE
    1.74
    BALL
    1.69
    HEAD
    1.59
     EDITION
    1.57
     AMERICA
    1.56
    FUL
    1.55
    ING
    1.55
    WOR
    1.54
    MAN
    1.54
    ERS
    1.51
    Activations Density 0.229%

    No Known Activations