Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 23954
    Prev
    Next
    INDEX
    Explanations

    expressions related to fear

    oai_token-act-pair · gpt-3.5-turbo

    expressions of fear

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 1 - fear

    No Comments

    Negative Logits
    arb
    -0.91
    urgy
    -0.84
    available
    -0.79
    arbon
    -0.76
    authors
    -0.75
    properties
    -0.74
    arkable
    -0.73
    added
    -0.71
    sample
    -0.70
    options
    -0.70
    POSITIVE LOGITS
    lessly
    1.22
     fear
    1.02
    mong
    0.98
    lessness
    0.96
     fears
    0.96
    ingly
    0.94
     lest
    0.93
    fully
    0.92
     afraid
    0.88
    fulness
    0.87
    Activations Density 0.014%

    No Known Activations