© 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. 15326
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "torture"

    oai_token-act-pair · gpt-3.5-turbo

    references to torture

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Darkness
    -0.78
     magnification
    -0.75
     donor
    -0.68
    lihood
    -0.66
     Farn
    -0.65
     Prospect
    -0.64
     brightest
    -0.64
    âĸ¬
    -0.63
     Manhattan
    -0.63
    FORE
    -0.62
    POSITIVE LOGITS
    urous
    1.43
    oise
    1.34
    illas
    1.08
    uring
    1.03
    uous
    1.01
    ured
    1.01
    urers
    0.98
    eur
    0.96
    imer
    0.94
    ures
    0.94
    Activations Density 0.005%

    No Known Activations