© 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. 0-RES-JB
    6. 19875
    Prev
    Next
    INDEX
    Explanations

    words related to active support or promotion of a cause or idea

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "advocates" or closely related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     runway
    -0.68
    leon
    -0.65
    uko
    -0.64
     snap
    -0.64
    chi
    -0.64
    cus
    -0.64
    nu
    -0.64
    chy
    -0.63
    ordon
    -0.62
     Phantom
    -0.62
    POSITIVE LOGITS
     advocates
    3.63
     proponents
    2.56
     advocate
    2.29
     advocacy
    1.95
     campaigners
    1.85
     Advoc
    1.81
     activists
    1.80
     supporters
    1.70
     adherents
    1.69
     critics
    1.60
    Activations Density 0.022%

    No Known Activations