© 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. 12-RES-JB
    11. 2810
    Prev
    Next
    INDEX
    Explanations

    information related to aviation, specific aircraft, and historical events surrounding aviation accidents

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to military aircraft and their operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebin
    -0.69
    Ô
    -0.68
     Speaking
    -0.67
     ARE
    -0.66
    Í
    -0.65
     tonight
    -0.64
    .:
    -0.64
     HERE
    -0.63
     Saying
    -0.63
     Recent
    -0.63
    POSITIVE LOGITS
     transitioned
    1.21
     began
    1.21
     retreated
    1.18
     froze
    1.18
     ceased
    1.18
     became
    1.17
     struggled
    1.16
     proceeded
    1.16
     drifted
    1.16
     withdrew
    1.15
    Activations Density 0.706%

    No Known Activations