© 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. 13386
    Prev
    Next
    INDEX
    Explanations

    words related to horror or fear

    oai_token-act-pair · gpt-3.5-turbo

    words related to a specific thematic or formal classification that includes various forms of 'hor'

    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
    ãģ®éŃĶ
    -0.81
    ãģ¦
    -0.74
    ERC
    -0.74
    enegger
    -0.71
    enhagen
    -0.71
    0000000000000000
    -0.70
    insula
    -0.70
    sburgh
    -0.70
    REDACTED
    -0.68
    anwhile
    -0.68
    POSITIVE LOGITS
    izons
    1.43
    izont
    1.23
    izontal
    1.22
    ror
    1.01
    oscope
    1.01
    izon
    1.00
    rible
    0.97
    ribly
    0.93
    osc
    0.87
    cru
    0.83
    Activations Density 0.009%

    No Known Activations