© 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. 3-RES-JB
    6. 1870
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Joe"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "oe"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifiers
    -0.68
     Chandra
    -0.65
     glim
    -0.64
     à¨
    -0.64
    ifier
    -0.64
    ifiable
    -0.63
     Sabha
    -0.62
     gist
    -0.59
     Attribution
    -0.59
    ãĥĥãĤ¯
    -0.58
    POSITIVE LOGITS
    ppel
    1.00
    zzi
    0.99
    oe
    0.96
    ze
    0.93
    cean
    0.90
    lete
    0.88
    hler
    0.88
    zy
    0.85
    utenant
    0.84
    zie
    0.83
    Activations Density 0.009%

    No Known Activations