© 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. 2-RES-JB
    6. 17282
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically the name "Cody" and "Edwin"

    oai_token-act-pair · gpt-3.5-turbo

    the names of individuals and products associated with creative works or projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boro
    -0.88
    comed
    -0.83
    sten
    -0.82
    ended
    -0.80
    umen
    -0.77
    ago
    -0.77
    pa
    -0.74
    uli
    -0.74
    ö
    -0.74
    arious
    -0.73
    POSITIVE LOGITS
     XD
    0.97
     Cutter
    0.95
     Cody
    0.84
     Bauer
    0.82
     CPC
    0.79
    SHIP
    0.75
    Capture
    0.74
     Kers
    0.73
     Fuj
    0.73
    xus
    0.73
    Activations Density 0.036%

    No Known Activations