© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 11203
    Prev
    Next
    INDEX
    Explanations

    mentions of specific organizations related to various policy, research, and legal matters

    oai_token-act-pair · gpt-3.5-turbo

    references to various advocacy centers and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WER
    -0.74
     lad
    -0.67
     entit
    -0.65
    soever
    -0.62
    minus
    -0.61
     conductor
    -0.61
    uckles
    -0.61
    RM
    -0.61
     composer
    -0.61
     prem
    -0.60
    POSITIVE LOGITS
     Disease
    1.05
     Inquiry
    0.99
     Investigative
    0.96
     Strategic
    0.93
     Excellence
    0.88
     Transformation
    0.86
     Addiction
    0.84
     Ecology
    0.82
     Economic
    0.82
     Analysis
    0.82
    Activations Density 0.024%

    No Known Activations