Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 19743
    Prev
    Next
    INDEX
    Explanations

    adjectives and verbs related to eagerness

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express eagerness or desire to take action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.75
    anchester
    -0.74
    vision
    -0.72
    llan
    -0.71
    erva
    -0.68
    calling
    -0.64
    aca
    -0.63
    ITIES
    -0.62
     è£ıè¦ļéĨĴ
    -0.59
    DAQ
    -0.58
    POSITIVE LOGITS
     impress
    1.00
     emulate
    0.94
     prove
    0.94
     please
    0.93
     maximize
    0.92
     capitalize
    0.87
     imitate
    0.87
     succeed
    0.86
    please
    0.85
     learn
    0.83
    Activations Density 0.145%

    No Known Activations