© 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. 11-RES-JB
    11. 18583
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations and entities in news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to specific nationalities or groups related to significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    _.
    -0.61
     nonetheless
    -0.55
     accordingly
    -0.53
     however
    -0.50
     descriptive
    -0.48
    *.
    -0.48
    herer
    -0.48
     foremost
    -0.48
     moreover
    -0.47
    +.
    -0.47
    POSITIVE LOGITS
     Belfast
    0.65
    zbollah
    0.65
    ocaust
    0.60
    chwitz
    0.57
     Rohingya
    0.55
     tyres
    0.53
     debt
    0.48
     illegally
    0.48
    DoS
    0.48
     rubbish
    0.48
    Activations Density 1.163%

    No Known Activations