© 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. 11-RES-JB
    11. 7772
    Prev
    Next
    INDEX
    Explanations

    mentions of specific titles or roles, likely related to technology or business

    oai_token-act-pair · gpt-3.5-turbo

    mentions of companies and industries related to technology and services

    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
     gh
    -0.95
    hai
    -0.83
    ghai
    -0.77
     pumpkin
    -0.77
     OnePlus
    -0.76
    âĺ
    -0.75
     Gh
    -0.73
    Gh
    -0.72
     mu
    -0.71
    zbollah
    -0.71
    POSITIVE LOGITS
     Ed
    2.28
    Ed
    2.13
     Edwards
    2.01
     ED
    1.69
     ed
    1.62
     Edmund
    1.41
    ED
    1.24
     Edward
    1.21
     Edwin
    1.20
     Edison
    1.18
    Activations Density 0.333%

    No Known Activations