© 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. 4-RES-JB
    11. 15299
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Noble"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Noble" and its variations

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

    No Comments

    Negative Logits
    Downloadha
    -0.98
    ablishment
    -0.88
     ultras
    -0.82
    utic
    -0.78
    icago
    -0.75
     Gork
    -0.74
    Ñı
    -0.72
    arella
    -0.72
    uders
    -0.67
     Bie
    -0.67
    POSITIVE LOGITS
    bridge
    1.00
    ãĥ©ãĥ³
    0.88
    Nob
    0.87
    minded
    0.77
     Phant
    0.76
     laureate
    0.76
    prising
    0.75
    shire
    0.73
    ridge
    0.72
    woman
    0.71
    Activations Density 0.013%

    No Known Activations