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. 11-RES-JB
    6. 634
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases indicating a tension, dilemma, or risky situation

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tremend
    -0.80
     unstoppable
    -0.74
     collide
    -0.74
     irresistible
    -0.73
     unbeat
    -0.73
     tyr
    -0.71
     barg
    -0.69
     extinct
    -0.68
     payday
    -0.68
     reeling
    -0.66
    POSITIVE LOGITS
     Instead
    2.52
    Instead
    2.19
     Rather
    2.09
     Nor
    1.97
     Nonetheless
    1.76
     Nevertheless
    1.75
    Rather
    1.72
    Nor
    1.61
    Nevertheless
    1.59
    Nonetheless
    1.55
    Activations Density 0.595%

    No Known Activations