© 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. 3-RES-JB
    11. 10738
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Gold" or related phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Gold," particularly in various contexts associated with individuals or awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ATIONS
    -0.87
    SPONSORED
    -0.74
    ROR
    -0.71
     constitu
    -0.65
    etheless
    -0.63
    FINE
    -0.62
    Downloadha
    -0.61
    chy
    -0.60
    ect
    -0.60
    uated
    -0.59
    POSITIVE LOGITS
    vertisement
    1.01
    smith
    0.95
     medal
    0.94
    wyn
    0.93
    mund
    0.92
    finger
    0.92
    stones
    0.90
     Medal
    0.90
    mining
    0.89
    mine
    0.88
    Activations Density 0.009%

    No Known Activations