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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 3520
    Prev
    Next
    INDEX
    Explanations

    instances where the document discusses people being affected or impacted by different situations or conditions

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express consequences or significant impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anus
    -0.68
    ascus
    -0.67
    thal
    -0.66
    jug
    -0.64
    oshenko
    -0.64
     pit
    -0.64
     hust
    -0.63
     emanc
    -0.63
    adi
    -0.63
    iber
    -0.62
    POSITIVE LOGITS
     Lastly
    1.00
     Eventually
    0.96
     However
    0.96
     Conversely
    0.95
     Otherwise
    0.92
     Afterwards
    0.90
     Therefore
    0.90
     Likewise
    0.89
     Additionally
    0.89
     Whereas
    0.89
    Activations Density 0.859%

    No Known Activations