© 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. 12493
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues and challenges faced by various groups within society

    oai_token-act-pair · gpt-3.5-turbo

    sentences related to fear and its impact on individuals, particularly migrants

    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
     sidx
    -0.77
     chuck
    -0.69
    pic
    -0.69
     Fool
    -0.67
     Comet
    -0.66
    Posts
    -0.65
     chuckle
    -0.64
     Cthulhu
    -0.63
     Fires
    -0.63
     Pumpkin
    -0.62
    POSITIVE LOGITS
     resettlement
    1.03
     UNHCR
    1.00
     careg
    0.87
    nesty
    0.85
     treatment
    0.84
     asylum
    0.82
     relief
    0.80
    reatment
    0.80
     deportation
    0.79
    ettlement
    0.79
    Activations Density 1.058%

    No Known Activations