© 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. 5063
    Prev
    Next
    INDEX
    Explanations

    terms related to the activity of conducting investigations or inquiries

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the act of conducting research

    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
     Leilan
    -0.75
     partic
    -0.69
    twitch
    -0.65
     Cancel
    -0.65
    alone
    -0.61
    ells
    -0.61
     Lann
    -0.60
     succession
    -0.60
    esm
    -0.59
    elo
    -0.59
    POSITIVE LOGITS
     psychology
    0.79
     researching
    0.79
    geist
    0.78
     psychologists
    0.77
     analyst
    0.77
    sonian
    0.74
     scholar
    0.74
     psychologist
    0.72
     resear
    0.70
    Ô
    0.70
    Activations Density 0.083%

    No Known Activations