© 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. 1-RES-JB
    11. 21946
    Prev
    Next
    INDEX
    Explanations

    the name "Nicol" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Nicol" and related entities

    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
    balls
    -0.89
    wards
    -0.78
    busters
    -0.71
    uits
    -0.70
    ward
    -0.64
     Devils
    -0.63
     dolls
    -0.62
     Barbie
    -0.62
    ansas
    -0.61
    ball
    -0.60
    POSITIVE LOGITS
    iven
    0.86
    theless
    0.84
    èĢħ
    0.81
    Sov
    0.80
    nen
    0.76
    nian
    0.74
    oÄŁ
    0.72
    hovah
    0.71
    ophers
    0.71
     Nicol
    0.71
    Activations Density 0.028%

    No Known Activations