© 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. 7-RES-JB
    11. 21487
    Prev
    Next
    INDEX
    Explanations

    mentions of physical pain or suffering

    oai_token-act-pair · gpt-3.5-turbo

    mentions of torture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Darkness
    -0.76
    lihood
    -0.67
     livest
    -0.67
     IST
    -0.67
     donor
    -0.66
     magnification
    -0.66
    âĸ¬
    -0.66
     brightest
    -0.63
     Prospect
    -0.62
     Hitman
    -0.62
    POSITIVE LOGITS
    urous
    1.47
    oise
    1.44
    illas
    1.13
    imer
    1.05
    uous
    1.00
    eur
    0.98
    urers
    0.98
    ured
    0.97
    oled
    0.96
    uring
    0.95
    Activations Density 0.028%

    No Known Activations