© 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. 4-RES-JB
    11. 12290
    Prev
    Next
    INDEX
    Explanations

    words related to fear or being afraid

    oai_token-act-pair · gpt-3.5-turbo

    expressions of fear or apprehension

    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
    robe
    -0.83
    rovers
    -0.81
    eret
    -0.79
    olitan
    -0.78
    byter
    -0.77
    lished
    -0.76
    endum
    -0.76
    area
    -0.74
    issance
    -0.73
    bard
    -0.73
    POSITIVE LOGITS
     afraid
    0.99
     lest
    0.80
    crow
    0.79
    ÃįÃį
    0.71
    NESS
    0.71
    oti
    0.71
     retribution
    0.69
    ptin
    0.69
     pregn
    0.67
     Ily
    0.65
    Activations Density 0.013%

    No Known Activations