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. 10-RES-JB
    6. 10042
    Prev
    Next
    INDEX
    Explanations

    words related to changes or growth over time

    oai_token-act-pair · gpt-3.5-turbo

    terms related to change and effectiveness in systems or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    USS
    -0.62
    acus
    -0.61
     Dug
    -0.58
    itan
    -0.57
    BuyableInstoreAndOnline
    -0.57
    istani
    -0.56
    Media
    -0.56
    yet
    -0.55
    rote
    -0.54
    bold
    -0.54
    POSITIVE LOGITS
     whenever
    1.33
     when
    1.30
    when
    1.17
     depending
    1.05
     spontaneously
    1.04
     periodically
    1.02
     automatically
    1.00
     WHEN
    0.98
     during
    0.97
     AFTER
    0.97
    Activations Density 0.411%

    No Known Activations