© 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. 19645
    Prev
    Next
    INDEX
    Explanations

    references to the Pentagon

    oai_token-act-pair · gpt-3.5-turbo

    references to the Pentagon

    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
    à
    -0.74
    lihood
    -0.71
    gger
    -0.71
    Hop
    -0.68
    cess
    -0.68
    Beer
    -0.68
     Constantin
    -0.66
    BOOK
    -0.65
    PER
    -0.65
    Ward
    -0.65
    POSITIVE LOGITS
     Pentagon
    1.07
     Papers
    0.92
    arium
    0.82
    ilion
    0.79
     brass
    0.77
    achev
    0.77
    selage
    0.77
     Plaza
    0.73
    eteria
    0.73
     contractors
    0.72
    Activations Density 0.007%

    No Known Activations