© 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. 0-RES-JB
    11. 20350
    Prev
    Next
    INDEX
    Explanations

    mentions or forms of the word "torture"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of torture and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elight
    -0.88
    ower
    -0.85
     Forward
    -0.69
    BG
    -0.68
     Dive
    -0.67
    Lv
    -0.67
    ready
    -0.67
    ople
    -0.66
     HQ
    -0.66
     Beacon
    -0.65
    POSITIVE LOGITS
     tort
    4.10
     Tort
    2.63
     torture
    1.55
     tortured
    1.53
     torment
    1.25
     tacos
    1.18
     rav
    1.06
     tor
    1.05
     taco
    1.05
     tam
    1.02
    Activations Density 0.016%

    No Known Activations