© 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. 1-RES-JB
    11. 9545
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations or titles with the word "Nu" in them

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the "Nu" entity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Corpse
    -0.85
    ivals
    -0.82
    é¾į
    -0.80
    ãĥĹ
    -0.79
    Jud
    -0.76
    ãĥŀ
    -0.72
    ãĤ·ãĥ£
    -0.72
    ãĥł
    -0.71
    éĹĺ
    -0.70
    ãģ®å®
    -0.69
    POSITIVE LOGITS
     Nu
    0.90
    nels
    0.89
    nery
    0.81
    undai
    0.80
    lator
    0.77
    entle
    0.74
     Ng
    0.73
    ilater
    0.69
    licks
    0.69
    awei
    0.69
    Activations Density 0.018%

    No Known Activations