© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 16667
    Prev
    Next
    INDEX
    Explanations

    words related to changes and fluctuations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to changes or variations in conditions, particularly in economic or population contexts

    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
     trivia
    -0.73
    manship
    -0.71
     irony
    -0.69
     judgement
    -0.68
     advoc
    -0.67
     hospitality
    -0.66
     princ
    -0.66
     congrat
    -0.66
     deserving
    -0.65
     elig
    -0.64
    POSITIVE LOGITS
    ued
    1.13
    ues
    1.06
    uted
    1.05
    pped
    1.03
    gged
    1.01
    uated
    1.00
    uate
    0.98
    ved
    0.97
    inished
    0.96
    then
    0.95
    Activations Density 0.089%

    No Known Activations