© 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. 2-RES-JB
    11. 10403
    Prev
    Next
    INDEX
    Explanations

    references to a specific football team named Atletico Madrid

    oai_token-act-pair · gpt-3.5-turbo

    references to the football club Atlético Madrid

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Operator
    -0.70
    natureconservancy
    -0.69
    orses
    -0.67
     unicorn
    -0.66
     Rider
    -0.63
    dar
    -0.61
    alos
    -0.61
     Gleaming
    -0.61
    ruby
    -0.60
    PASS
    -0.60
    POSITIVE LOGITS
    unia
    0.90
    letico
    0.88
    ÄŁ
    0.87
     Madrid
    0.86
    ichi
    0.83
    ibo
    0.80
    emouth
    0.76
    inho
    0.76
    medi
    0.76
    isans
    0.74
    Activations Density 0.022%

    No Known Activations