© 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. 4-RES-JB
    11. 22157
    Prev
    Next
    INDEX
    Explanations

    mentions of hybrid objects or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to hybrid technologies or concepts

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

    No Comments

    Negative Logits
    yers
    -0.90
    cloth
    -0.82
    useum
    -0.76
    ourning
    -0.74
     Lumpur
    -0.74
    hang
    -0.72
    enance
    -0.71
    achers
    -0.70
    soc
    -0.70
     Janeiro
    -0.70
    POSITIVE LOGITS
     hybrid
    0.95
    ization
    0.93
     hybrids
    0.90
    izations
    0.73
    ized
    0.67
     versions
    0.66
    icide
    0.66
    icides
    0.66
    idad
    0.65
    ity
    0.65
    Activations Density 0.010%

    No Known Activations