© 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. 16378
    Prev
    Next
    INDEX
    Explanations

    occurrences of the specific term "Nu"

    oai_token-act-pair · gpt-3.5-turbo
    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
    代
    -0.91
    iazep
    -0.87
    fried
    -0.74
    Lv
    -0.73
    matched
    -0.70
    pers
    -0.69
    readable
    -0.67
    inning
    -0.67
    ravis
    -0.66
    acus
    -0.66
    POSITIVE LOGITS
     Disc
    2.05
    Disc
    1.82
     Nu
    1.64
     nu
    1.44
     rim
    1.25
     Rim
    1.11
     Dum
    1.10
    esa
    1.08
     Campus
    1.08
     trumpet
    1.05
    Activations Density 0.043%

    No Known Activations