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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 17226
    Prev
    Next
    INDEX
    Explanations

    instances of the word "very."

    oai_token-act-pair · gpt-3.5-turbo

    the word "very" and its usage 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
    igi
    -0.71
    olor
    -0.71
    osal
    -0.69
    izational
    -0.66
    imus
    -0.64
    ensis
    -0.64
    sburgh
    -0.64
    iture
    -0.62
    onis
    -0.61
     Chronicle
    -0.61
    POSITIVE LOGITS
     much
    0.88
     similar
    0.85
     seldom
    0.83
     different
    0.82
     rarely
    0.80
    much
    0.80
     rare
    0.79
     handy
    0.79
     MUCH
    0.79
     unlikely
    0.79
    Activations Density 0.076%

    No Known Activations