© 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. 19758
    Prev
    Next
    INDEX
    Explanations

    Italian words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    words related to coffee and WiFi

    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
    ems
    -0.77
     Kurd
    -0.72
    rup
    -0.70
    gur
    -0.70
    ring
    -0.68
    makers
    -0.67
     Nanto
    -0.65
     Measures
    -0.65
    oyer
    -0.64
     disse
    -0.64
    POSITIVE LOGITS
    ICAN
    0.97
    uca
    0.83
    UX
    0.78
    ione
    0.73
    sburgh
    0.73
    ipop
    0.73
    ican
    0.70
    TPS
    0.68
    username
    0.66
    icone
    0.66
    Activations Density 0.018%

    No Known Activations