© 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. 12215
    Prev
    Next
    INDEX
    Explanations

    names or terms related to "Nak" or "Nom."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names, particularly "Nak" and "Satoshi."

    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
     Hercules
    -0.72
    DVD
    -0.70
     Nept
    -0.69
     ILCS
    -0.65
     Warwick
    -0.64
     seas
    -0.63
     Devon
    -0.63
     opener
    -0.62
     Pyro
    -0.62
     theat
    -0.62
    POSITIVE LOGITS
    amura
    1.24
    amoto
    1.19
    imura
    1.06
    ril
    1.04
    ay
    1.02
    aya
    1.01
    oda
    1.01
     Nak
    1.00
    itary
    1.00
    iri
    0.96
    Activations Density 0.006%

    No Known Activations