© 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. 7-RES-JB
    11. 18823
    Prev
    Next
    INDEX
    Explanations

    references to Wall Street

    oai_token-act-pair · gpt-3.5-turbo

    references to Wall Street and associated financial topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.75
     Ake
    -0.70
    lihood
    -0.70
     confir
    -0.68
    netflix
    -0.67
    mble
    -0.67
    forth
    -0.66
     orally
    -0.65
     afore
    -0.62
     Carbuncle
    -0.62
    POSITIVE LOGITS
    icial
    0.87
    ocratic
    0.86
    ocrat
    0.85
    urrency
    0.82
    opoly
    0.81
     banking
    0.81
    papers
    0.80
    acea
    0.80
    Money
    0.78
    abies
    0.77
    Activations Density 0.020%

    No Known Activations