© 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. 12606
    Prev
    Next
    INDEX
    Explanations

    scientific or technical terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    different classifications or categories indicated by the word "type."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    pload
    -0.71
     Bots
    -0.69
     Rings
    -0.67
    姫
    -0.66
    Leaks
    -0.66
    iae
    -0.65
     Zimmer
    -0.62
     Nadu
    -0.61
    olulu
    -0.61
     Bills
    -0.61
    POSITIVE LOGITS
    face
    1.39
    faces
    1.23
    casting
    1.03
    etter
    1.00
    etting
    0.96
    ahead
    0.95
    cast
    0.85
    classes
    0.80
    alias
    0.78
    of
    0.73
    Activations Density 0.029%

    No Known Activations