© 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. 6-RES-JB
    11. 249
    Prev
    Next
    INDEX
    Explanations

    sentences related to positive relationships and friendships

    oai_token-act-pair · gpt-3.5-turbo

    themes of genuine friendship and connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    govtrack
    -0.63
    displayText
    -0.61
     Investor
    -0.60
     Citation
    -0.58
    cedented
    -0.54
     Nationwide
    -0.54
    reports
    -0.53
    DEN
    -0.53
    raltar
    -0.53
    reported
    -0.53
    POSITIVE LOGITS
     diaper
    0.75
     princess
    0.73
     shit
    0.71
     shitty
    0.70
     oppressed
    0.69
     boobs
    0.68
     badass
    0.67
     girlfriends
    0.67
     fucking
    0.66
     dick
    0.66
    Activations Density 1.351%

    No Known Activations