© 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. 4-RES-JB
    11. 1574
    Prev
    Next
    INDEX
    Explanations

    terms related to the James Bond franchise

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the character James Bond

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

    No Comments

    Negative Logits
    OURCE
    -0.83
    itably
    -0.81
    seless
    -0.80
    resents
    -0.78
    ãĥ³ãĤ¸
    -0.77
    oaded
    -0.73
    pite
    -0.73
    usra
    -0.73
    à¼
    -0.71
    NPR
    -0.71
    POSITIVE LOGITS
     Bond
    1.03
    eson
    0.84
     Bonds
    0.81
    sov
    0.78
    minster
    0.78
    eering
    0.75
    ing
    0.74
    holes
    0.74
     Rib
    0.73
    eer
    0.72
    Activations Density 0.008%

    No Known Activations