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. 10-RES-JB
    6. 21892
    Prev
    Next
    INDEX
    Explanations

    words related to organizing events or gatherings

    oai_token-act-pair · gpt-3.5-turbo

    references to meetings and gatherings being organized or convened

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ats
    -0.73
     calves
    -0.67
     overboard
    -0.66
     calf
    -0.65
    ates
    -0.65
    ows
    -0.64
    ated
    -0.62
     apples
    -0.62
    enko
    -0.61
     throats
    -0.61
    POSITIVE LOGITS
    ility
    1.02
    lished
    0.90
    bourg
    0.85
    ilities
    0.82
    åĤ
    0.81
    lé
    0.81
    lies
    0.80
    miah
    0.76
    iliar
    0.76
    lance
    0.75
    Activations Density 0.105%

    No Known Activations