© 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. 2-RES-JB
    11. 13004
    Prev
    Next
    INDEX
    Explanations

    names of ancient Greek cities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city of Athens and historical figures associated with it

    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
    Trend
    -0.87
    isSpecialOrderable
    -0.79
    LLOW
    -0.78
    yy
    -0.78
    irts
    -0.74
    loo
    -0.72
    dyl
    -0.72
    dar
    -0.71
    CTV
    -0.71
    orter
    -0.69
    POSITIVE LOGITS
     Athens
    1.30
     Athen
    1.13
     traged
    0.92
     Spart
    0.82
     Socrates
    0.78
    sburg
    0.77
    terness
    0.77
     Ragnarok
    0.76
     Olympia
    0.76
     Corinth
    0.73
    Activations Density 0.016%

    No Known Activations