© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 11-RES-JB
    11. 13002
    Prev
    Next
    INDEX
    Explanations

    phrases related to ensuring safety, security, and maintenance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ensuring safety and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otom
    -0.77
    oaded
    -0.71
     Unsure
    -0.69
    itcher
    -0.68
    elman
    -0.67
    ooked
    -0.67
    rams
    -0.67
    wic
    -0.67
    ahime
    -0.65
    DragonMagazine
    -0.62
    POSITIVE LOGITS
     wellbeing
    1.68
     safety
    1.58
     survival
    1.53
     stability
    1.42
     welfare
    1.37
     viability
    1.34
     prosperity
    1.33
    safety
    1.32
     happiness
    1.32
     longevity
    1.30
    Activations Density 0.252%

    No Known Activations