© 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. 22897
    Prev
    Next
    INDEX
    Explanations

    the word "anc" with different intensities of activation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Lance" or variations of it

    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
     Typhoon
    -0.79
     IMAGES
    -0.70
    ãĥīãĥ©
    -0.67
     Dresden
    -0.65
     Mankind
    -0.65
     Birch
    -0.64
     Hitman
    -0.64
     Dare
    -0.64
     Pax
    -0.64
    ãĢIJ
    -0.62
    POSITIVE LOGITS
    anc
    1.12
    orp
    1.09
    ourt
    0.97
    rop
    0.93
    ancel
    0.92
    risis
    0.92
    olor
    0.92
    ath
    0.92
    iless
    0.91
    itizen
    0.89
    Activations Density 0.007%

    No Known Activations