© 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. 9-RES-JB
    11. 5622
    Prev
    Next
    INDEX
    Explanations

    names of countries and regions

    oai_token-act-pair · gpt-3.5-turbo

    references to geopolitical entities and relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lance
    -0.85
    laws
    -0.77
    BILITIES
    -0.69
    isks
    -0.68
    regor
    -0.67
    stones
    -0.66
    lesi
    -0.66
    cd
    -0.65
    ĵĺ
    -0.65
    ateurs
    -0.63
    POSITIVE LOGITS
     ratio
    1.45
     Ratio
    1.36
     ratios
    1.28
     hybrids
    1.28
     hybrid
    1.24
     combo
    1.23
     partnership
    1.18
     dich
    1.17
     relations
    1.16
     relationship
    1.15
    Activations Density 0.232%

    No Known Activations