© 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. 2-RES-JB
    11. 9323
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Wu"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Wu" and references related to the Wu-Tang brand or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Solitaire
    -0.73
     Cassandra
    -0.68
     Corvette
    -0.67
     Passenger
    -0.66
     Amtrak
    -0.64
     Drawn
    -0.63
    */(
    -0.62
    pmwiki
    -0.61
     mileage
    -0.60
     pige
    -0.60
    POSITIVE LOGITS
    wu
    0.98
    atche
    0.96
    ille
    0.93
    pei
    0.89
    auld
    0.88
    ivas
    0.86
    hei
    0.84
    zers
    0.82
    aji
    0.81
    ety
    0.80
    Activations Density 0.009%

    No Known Activations