© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 3187
    Prev
    Next
    INDEX
    Explanations

    organizations or groups related to specific professions or interests

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    efully
    -0.74
    lier
    -0.71
    aneously
    -0.64
    rous
    -0.62
    lying
    -0.60
    frog
    -0.58
     fisherman
    -0.57
    locks
    -0.57
    verts
    -0.57
     drums
    -0.57
    POSITIVE LOGITS
    hip
    1.33
    paces
    1.20
    pace
    1.19
    hift
    1.14
    ystem
    1.11
    hips
    1.08
    '
    1.06
    kaya
    1.04
    aurus
    1.03
     Guild
    1.00
    Activations Density 0.246%

    No Known Activations