© 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. 9622
    Prev
    Next
    INDEX
    Explanations

    keywords related to optional items or actions

    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
    imaru
    -0.86
    ells
    -0.81
    Swe
    -0.77
    iw
    -0.76
    encers
    -0.75
    BW
    -0.74
    ruary
    -0.74
    abal
    -0.73
    ards
    -0.73
    wordpress
    -0.72
    POSITIVE LOGITS
     extras
    0.98
     accessory
    0.86
     bonus
    0.85
     extra
    0.82
     accessories
    0.74
     supplemental
    0.72
     optional
    0.72
     eaves
    0.71
     foil
    0.71
     gadget
    0.71
    Activations Density 0.045%

    No Known Activations