© 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. 9-RES-JB
    11. 10175
    Prev
    Next
    INDEX
    Explanations

    names of specific individuals, likely related to policy, environmental science, or humanitarian efforts

    oai_token-act-pair · gpt-3.5-turbo

    names and titles of individuals involved in organizational or governmental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subsistence
    -0.62
     underwater
    -0.60
     consumers
    -0.58
     envy
    -0.57
     Colossus
    -0.57
     manufacturing
    -0.55
     mob
    -0.55
     ultras
    -0.55
     manipulating
    -0.55
     charity
    -0.54
    POSITIVE LOGITS
    ansky
    1.15
    inski
    1.11
    acci
    1.10
    kson
    1.07
    zinski
    1.06
    atz
    1.05
    opoulos
    1.05
    enberg
    1.05
    baugh
    1.04
    owski
    1.04
    Activations Density 0.620%

    No Known Activations