© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 22520
    Prev
    Next
    INDEX
    Explanations

    the name "Dion Phaneuf" followed by a variation of a positive adjective

    oai_token-act-pair · gpt-3.5-turbo

    words and terms related to substances and their uses

    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
    ntil
    -0.85
    lished
    -0.76
    irements
    -0.76
    ODUCT
    -0.70
    achusetts
    -0.70
     carbohyd
    -0.69
    è¦ļéĨĴ
    -0.69
    aeper
    -0.69
    rador
    -0.68
    rium
    -0.68
    POSITIVE LOGITS
    ane
    1.07
    cia
    0.91
    leigh
    0.84
    gas
    0.84
    ffe
    0.82
    jad
    0.77
    gan
    0.76
    ase
    0.76
    quin
    0.74
    geon
    0.72
    Activations Density 0.016%

    No Known Activations