© 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. 24424
    Prev
    Next
    INDEX
    Explanations

    mentions of friends and family in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to friends, family, and social connections

    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
    ãĥķãĤ©
    -0.75
     gears
    -0.74
     counterfe
    -0.68
     brim
    -0.67
    DEBUG
    -0.67
    ntax
    -0.63
    iculture
    -0.63
     Reprodu
    -0.61
    GMT
    -0.61
    RANT
    -0.61
    POSITIVE LOGITS
     acquaintances
    1.40
     coworkers
    1.24
     classmates
    1.19
     colleagues
    1.16
     relatives
    1.15
     colleague
    1.12
     strangers
    1.11
     neighbours
    1.02
     neighbors
    1.02
     family
    1.02
    Activations Density 0.252%

    No Known Activations