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. 3-RES-JB
    6. 1244
    Prev
    Next
    INDEX
    Explanations

    sentences mentioning the concept of "spare time."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "spare" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ablishment
    -0.77
    anwhile
    -0.70
     appropri
    -0.68
    uador
    -0.66
    aminer
    -0.66
     detrim
    -0.63
    hedral
    -0.63
    Reviewed
    -0.63
    idable
    -0.62
    rus
    -0.62
    POSITIVE LOGITS
     spare
    0.98
     tire
    0.80
    capacity
    0.69
     spared
    0.68
    plane
    0.68
     IPM
    0.67
    pering
    0.66
    ricular
    0.65
    zzi
    0.65
     beds
    0.65
    Activations Density 0.007%

    No Known Activations