© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 17390
    Prev
    Next
    INDEX
    Explanations

    phrases related to official committees or task forces being established or assigned to investigate or study various issues

    oai_token-act-pair · gpt-3.5-turbo

    references to organizational structures and committees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Advantage
    -0.79
    ãĤ¨ãĥ«
    -0.78
    SourceFile
    -0.73
     Tile
    -0.69
    bucks
    -0.69
     Tide
    -0.68
    ulia
    -0.66
    ãĤ¦ãĤ¹
    -0.65
     Avenger
    -0.64
    rill
    -0.64
    POSITIVE LOGITS
     convened
    1.53
     chaired
    1.38
     tasked
    1.24
     investigating
    1.13
     appointed
    1.11
     overseeing
    1.09
     comprising
    1.08
     headed
    1.08
     composed
    1.05
     disbanded
    1.04
    Activations Density 0.190%

    No Known Activations