© 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. 0-RES-JB
    11. 11864
    Prev
    Next
    INDEX
    Explanations

    references to various forms and contexts of torture

    oai_token-act-pair · gpt-3.5-turbo

    references to torture and related themes

    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
     Redmond
    -0.87
    ipient
    -0.78
     Iss
    -0.72
     RR
    -0.70
     Horizons
    -0.70
     RN
    -0.69
     KB
    -0.69
    imer
    -0.69
    Ren
    -0.68
    isd
    -0.68
    POSITIVE LOGITS
     torture
    3.82
     tortured
    2.24
     interrogation
    1.91
     Tort
    1.91
     tort
    1.63
     torment
    1.59
     detention
    1.45
     interrog
    1.42
     brutality
    1.35
     imprison
    1.34
    Activations Density 0.025%

    No Known Activations