© 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. 12957
    Prev
    Next
    INDEX
    Explanations

    phrases related to the surname "Gol" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or entity named "Gol."

    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
    è¦ļéĨĴ
    -0.79
    riad
    -0.76
     Highly
    -0.74
    Rated
    -0.69
    akers
    -0.68
    lied
    -0.68
     NCT
    -0.66
    shapeshifter
    -0.66
    ensional
    -0.66
     Trilogy
    -0.63
    POSITIVE LOGITS
     Gol
    1.04
    mud
    0.94
    atility
    0.92
    anguage
    0.92
    unte
    0.88
    ideon
    0.85
    nown
    0.84
    entle
    0.82
    otiation
    0.82
    oshenko
    0.80
    Activations Density 0.003%

    No Known Activations