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

    Neuronpedia

    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. 1-RES-JB
    11. 14398
    Prev
    Next
    INDEX
    Explanations

    names or terms related to the name "Neill"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Neill" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     haste
    -0.81
    Ranked
    -0.74
    amaz
    -0.73
    nces
    -0.72
    updated
    -0.70
    href
    -0.68
    ENCY
    -0.68
    dayName
    -0.66
    è¯
    -0.66
    Offline
    -0.66
    POSITIVE LOGITS
    Neill
    1.05
    igon
    0.88
     Enterprises
    0.85
    uth
    0.84
    arty
    0.83
    oyd
    0.82
    quist
    0.82
    igan
    0.82
    cliffe
    0.81
    theless
    0.80
    Activations Density 0.006%

    No Known Activations