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. 2-RES-JB
    6. 9937
    Prev
    Next
    INDEX
    Explanations

    words related to fear or being afraid

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "feared" indicating anxiety or concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 2 - fear

    No Comments

    Negative Logits
    arb
    -0.96
    urgy
    -0.91
    arist
    -0.84
    versions
    -0.84
    artisan
    -0.81
    ced
    -0.81
    version
    -0.80
    ysis
    -0.79
    ighters
    -0.75
    ammy
    -0.75
    POSITIVE LOGITS
    lessly
    0.98
     feared
    0.86
     fears
    0.84
     lest
    0.82
     Ily
    0.80
     afraid
    0.79
     Esther
    0.71
     fearing
    0.71
    fully
    0.70
    FUL
    0.69
    Activations Density 0.009%

    No Known Activations