© 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. 1-RES-JB
    11. 3225
    Prev
    Next
    INDEX
    Explanations

    references to organizations such as OECD and OPEC in economic contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to international organizations and economic indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    packs
    -0.83
    flies
    -0.83
    fly
    -0.77
    chief
    -0.74
    pite
    -0.72
    geon
    -0.72
    light
    -0.72
    history
    -0.69
    adows
    -0.69
    illa
    -0.68
    POSITIVE LOGITS
     OECD
    1.23
    ECD
    0.81
     citiz
    0.78
     unemploy
    0.76
     Countries
    0.69
    ratulations
    0.66
     Sabha
    0.65
     Osc
    0.65
     Cooperation
    0.65
     Institution
    0.65
    Activations Density 0.010%

    No Known Activations