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. 2-RES-JB
    6. 19248
    Prev
    Next
    INDEX
    Explanations

    words related to rapid growth or escalation

    oai_token-act-pair · gpt-3.5-turbo

    metaphors related to growth and momentum, particularly those associated with snowballs and avalanches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eem
    -0.90
    senal
    -0.71
    olphins
    -0.71
    mite
    -0.71
    aving
    -0.71
    rongh
    -0.69
    haps
    -0.68
    pez
    -0.66
    placed
    -0.66
    cius
    -0.65
    POSITIVE LOGITS
     snowball
    1.20
     cascade
    0.89
     avalanche
    0.75
     convol
    0.74
     pandemonium
    0.73
    result
    0.69
     Bok
    0.67
    usercontent
    0.67
     Pengu
    0.67
     ILCS
    0.66
    Activations Density 0.015%

    No Known Activations