© 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. 3-RES-JB
    11. 7257
    Prev
    Next
    INDEX
    Explanations

    phrases or words indicating a person or entity is outspoken on a particular topic

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "outspoken."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akeru
    -0.90
    pty
    -0.90
    uden
    -0.79
    ummies
    -0.73
    ramid
    -0.69
    atch
    -0.69
    opes
    -0.68
    asus
    -0.67
    abases
    -0.67
     Girls
    -0.66
    POSITIVE LOGITS
    ness
    0.97
     outspoken
    0.92
     personalities
    0.82
     critic
    0.79
     activist
    0.76
    iveness
    0.75
     activism
    0.74
    hip
    0.73
     campaigner
    0.73
     criticism
    0.73
    Activations Density 0.020%

    No Known Activations