© 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. 3-RES-JB
    11. 12281
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to the name "Nana" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the element "Na" (sodium) in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tails
    -0.74
    wolves
    -0.72
     Cosponsors
    -0.71
    library
    -0.70
    RFC
    -0.70
    neys
    -0.70
    tracks
    -0.69
    mop
    -0.66
    Reviewed
    -0.66
    displayText
    -0.65
    POSITIVE LOGITS
    eus
    1.16
    uthor
    1.14
    ïve
    0.90
    isance
    0.89
    uth
    0.86
    vel
    0.86
    ñ
    0.86
    ples
    0.86
    veland
    0.86
    wn
    0.86
    Activations Density 0.009%

    No Known Activations