© 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. 24170
    Prev
    Next
    INDEX
    Explanations

    statistics related to various causes of deaths and other numerical data

    oai_token-act-pair · gpt-3.5-turbo

    statistics and figures related to health and safety issues

    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
     sche
    -0.74
     directional
    -0.69
    terior
    -0.67
    ãĤ¤ãĥĪ
    -0.67
     procedural
    -0.66
    fml
    -0.66
    tone
    -0.66
    tones
    -0.65
     POV
    -0.65
    oké
    -0.65
    POSITIVE LOGITS
    population
    1.15
     estimated
    1.07
     annually
    1.03
     population
    1.00
     worldwide
    0.98
    Population
    0.98
    Ranked
    0.97
     Population
    0.96
     annual
    0.95
     GDP
    0.95
    Activations Density 1.509%

    No Known Activations