© 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. 1539
    Prev
    Next
    INDEX
    Explanations

    the name "Neal" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Neal" or related terms

    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
    teen
    -0.88
    luster
    -0.71
     scant
    -0.69
    stood
    -0.68
    gamer
    -0.67
    UID
    -0.66
    fare
    -0.66
    VALUE
    -0.66
     Prevent
    -0.63
    teenth
    -0.62
    POSITIVE LOGITS
     Neal
    1.02
     Stephenson
    0.94
    isson
    0.87
    ison
    0.83
    Neal
    0.82
    eree
    0.78
    sburg
    0.78
    eting
    0.78
     Cass
    0.76
     Katy
    0.74
    Activations Density 0.010%

    No Known Activations