© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 14836
    Prev
    Next
    INDEX
    Explanations

    words related to fears and anxieties

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases expressing fear and anxiety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 4 - fear

    No Comments

    Negative Logits
    Products
    -0.74
    drivers
    -0.73
    çĦ
    -0.72
    mes
    -0.69
    liga
    -0.67
    interface
    -0.67
     Sabha
    -0.64
    gow
    -0.62
     Osc
    -0.60
    sheets
    -0.60
    POSITIVE LOGITS
    icist
    0.71
    inus
    0.69
     mediation
    0.64
    iful
    0.62
    ierrez
    0.60
    stic
    0.60
     fighter
    0.59
     disciple
    0.59
     Bucc
    0.59
     nerve
    0.59
    Activations Density 0.025%

    No Known Activations