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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 1235
    Prev
    Next
    INDEX
    Explanations

    entities or concepts containing the partial word "nu"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "nu" or similar terms, often in a repeated context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INE
    -0.79
    ggle
    -0.76
     Trotsky
    -0.75
    aucus
    -0.70
     Crisis
    -0.69
     Twain
    -0.69
     Chomsky
    -0.69
     dogged
    -0.68
    obook
    -0.67
     Banking
    -0.67
    POSITIVE LOGITS
     nu
    2.30
    nu
    1.94
     intentional
    1.39
    oki
    1.16
     Nu
    1.15
     ok
    1.13
     nuisance
    1.05
    rish
    1.04
    Ky
    1.04
     interf
    1.03
    Activations Density 0.051%

    No Known Activations