© 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. 9837
    Prev
    Next
    INDEX
    Explanations

    mentions of political affiliations and groups, particularly in the context of lawmakers and legislation

    oai_token-act-pair · gpt-3.5-turbo

    commas that indicate list-like structures or separations in complex information

    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
    teenth
    -0.72
    washer
    -0.66
    ield
    -0.66
    eur
    -0.65
    ģĸ
    -0.63
    =#
    -0.62
    gap
    -0.61
    asis
    -0.59
     tha
    -0.58
    iku
    -0.58
    POSITIVE LOGITS
     including
    1.23
    including
    1.09
    particularly
    1.04
     Including
    1.00
    especially
    0.99
     meanwhile
    0.97
     rejoice
    0.96
     however
    0.96
     notably
    0.90
     moreover
    0.89
    Activations Density 0.200%

    No Known Activations