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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 16376
    Prev
    Next
    INDEX
    Explanations

    time-related phrases or statements with the word "until"

    oai_token-act-pair · gpt-3.5-turbo

    the word "until" indicating temporal conditions or limitations

    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
    cap
    -0.71
    pour
    -0.70
    Nic
    -0.69
    eas
    -0.68
    Rated
    -0.66
    Maker
    -0.66
    hazard
    -0.66
    aque
    -0.66
    Friend
    -0.66
    cult
    -0.65
    POSITIVE LOGITS
    terday
    0.78
    soever
    0.76
    MENTS
    0.72
    alde
    0.72
     afterward
    0.66
    ruciating
    0.65
    ittle
    0.65
    swer
    0.64
     Til
    0.64
    opa
    0.64
    Activations Density 0.028%

    No Known Activations