© 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. 15563
    Prev
    Next
    INDEX
    Explanations

    terms related to architecture and architects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to architecture and architects

    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
    TPS
    -0.74
    eworthy
    -0.72
    mma
    -0.67
    zees
    -0.66
    othal
    -0.66
    cow
    -0.64
    ties
    -0.62
    awar
    -0.62
    "]=>
    -0.62
    Redd
    -0.61
    POSITIVE LOGITS
    urally
    1.60
    itect
    1.34
    ural
    1.30
     architect
    1.01
     architects
    0.90
     architectural
    0.83
     Architecture
    0.80
     Architects
    0.80
     Architect
    0.80
    urated
    0.78
    Activations Density 0.074%

    No Known Activations