© 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. 10-RES-JB
    11. 8562
    Prev
    Next
    INDEX
    Explanations

    mentions of specific entities like companies, sports teams, and political parties

    oai_token-act-pair · gpt-3.5-turbo

    mentions of organizations or groups, particularly in a business or team context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ystem
    -0.67
    azo
    -0.67
    mith
    -0.65
    alam
    -0.64
    lap
    -0.64
    Ô
    -0.60
    NetMessage
    -0.60
    ewitness
    -0.59
    cott
    -0.59
    è¦
    -0.59
    POSITIVE LOGITS
     itself
    1.12
    's
    0.91
    osphere
    0.90
    iverse
    0.83
     hierarchy
    0.78
     fold
    0.67
     proper
    0.66
    ÃŃs
    0.63
     ecosystem
    0.63
    atics
    0.62
    Activations Density 0.319%

    No Known Activations