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. 7-RES-JB
    6. 10266
    Prev
    Next
    INDEX
    Explanations

    phrases related to sudden or impactful events or movements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate sudden or impactful appearances and movements within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rss
    -0.68
     subcontract
    -0.66
    illary
    -0.64
     stub
    -0.63
    few
    -0.63
    ortunate
    -0.61
    itus
    -0.60
    obyl
    -0.60
     Caption
    -0.60
     tunnel
    -0.59
    POSITIVE LOGITS
     applause
    0.83
     ecstasy
    0.80
    waves
    0.77
    iously
    0.73
    ocity
    0.73
     headlines
    0.71
     popularity
    0.71
    EED
    0.70
     havoc
    0.70
     acclaim
    0.70
    Activations Density 0.289%

    No Known Activations