© 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. 6-RES-JB
    11. 10758
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences containing instances of the word "involved."

    oai_token-act-pair · gpt-3.5-turbo

    references to parties or entities associated with specific events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ander
    -0.66
    \\\\\\\\
    -0.66
    Jet
    -0.64
    mares
    -0.64
    efully
    -0.63
    haar
    -0.62
    atters
    -0.62
    imon
    -0.61
    ppel
    -0.61
    IFIC
    -0.61
    POSITIVE LOGITS
    ioned
    0.80
     involved
    0.70
    cius
    0.68
    involved
    0.66
     implicated
    0.65
    enza
    0.64
    nikov
    0.64
    olved
    0.61
    itaire
    0.61
    ulkan
    0.60
    Activations Density 0.024%

    No Known Activations