© 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. 6-RES-JB
    11. 5113
    Prev
    Next
    INDEX
    Explanations

    first person pronouns ('I', 'we')

    oai_token-act-pair · gpt-3.5-turbo

    first-person plural and singular pronouns as well as expressions of personal opinion or experience

    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
     tradem
    -0.63
     Ez
    -0.63
     Templar
    -0.62
    mone
    -0.62
    staking
    -0.60
     coli
    -0.58
     helic
    -0.57
    lic
    -0.56
    artisan
    -0.56
    oÄŁ
    -0.55
    POSITIVE LOGITS
     Learned
    0.86
    ãĤ»
    0.86
     happened
    0.82
    azes
    0.74
     happ
    0.73
     happens
    0.72
    Lear
    0.71
    SPONSORED
    0.70
    Ĥª
    0.67
    quickShipAvailable
    0.67
    Activations Density 0.094%

    No Known Activations