© 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. 314
    Prev
    Next
    INDEX
    Explanations

    references related to the concept of "tap", which could relate to various contexts such as tap dancing, tap water, or tap rooms

    oai_token-act-pair · gpt-3.5-turbo
    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
    ============
    -0.69
     AMERICA
    -0.67
    anchester
    -0.59
     Bram
    -0.58
    ========
    -0.58
     Lynd
    -0.58
    Reloaded
    -0.58
     Warsaw
    -0.56
    cens
    -0.56
     Monstrous
    -0.56
    POSITIVE LOGITS
    roots
    1.01
    eless
    0.98
    root
    0.97
    acity
    0.96
    ering
    0.96
    eful
    0.89
    istry
    0.85
    room
    0.81
    pour
    0.81
    rooms
    0.78
    Activations Density 0.042%

    No Known Activations