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. 8-RES-JB
    6. 18195
    Prev
    Next
    INDEX
    Explanations

    recent events or actions that have just occurred

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "just" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pett
    -0.61
    AppData
    -0.60
     necks
    -0.60
    amen
    -0.60
    risk
    -0.59
     quo
    -0.59
    similar
    -0.58
     Likely
    -0.57
     anytime
    -0.57
     disproportionately
    -0.57
    POSITIVE LOGITS
    ifiable
    1.05
    ifications
    0.96
    ifi
    0.91
    itia
    0.90
    if
    0.90
    IFIC
    0.87
    IFIED
    0.85
    iffe
    0.80
    iciary
    0.78
    ifiers
    0.77
    Activations Density 0.072%

    No Known Activations