© 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. 4-RES-JB
    11. 15389
    Prev
    Next
    INDEX
    Explanations

    finance-related entities and concepts, specifically focusing on financial institutions and activities

    oai_token-act-pair · gpt-3.5-turbo

    references to financial entities or banking terms

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

    No Comments

    Negative Logits
    ggle
    -0.59
    emporary
    -0.49
    ergy
    -0.49
    WAR
    -0.48
    gypt
    -0.48
    erb
    -0.48
    raft
    -0.47
    IFF
    -0.47
    ZI
    -0.46
    bernatorial
    -0.46
    POSITIVE LOGITS
     notwithstanding
    0.65
    ãĥĩãĤ£
    0.59
    ãĥĺ
    0.55
     è£ıè
    0.54
     plat
    0.52
     compr
    0.50
     pal
    0.50
    !).
    0.50
    ãĤ±
    0.49
    conservancy
    0.49
    Activations Density 3.146%

    No Known Activations