© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 11287
    Prev
    Next
    INDEX
    Explanations

    specific examples of individuals or groups, including politicians, lawmakers, and officials

    oai_token-act-pair · gpt-3.5-turbo

    phrases introducing lists or groups of people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asis
    -0.67
    eur
    -0.65
    aukee
    -0.65
    washer
    -0.64
    eus
    -0.63
    ");
    -0.62
    igmatic
    -0.62
    ield
    -0.62
    gap
    -0.60
    inqu
    -0.57
    POSITIVE LOGITS
     including
    1.15
     meanwhile
    1.06
     rejoice
    1.04
    including
    1.03
     however
    0.96
    particularly
    0.94
     moreover
    0.93
    especially
    0.91
     especially
    0.89
     unsurprisingly
    0.88
    Activations Density 0.220%

    No Known Activations