© 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. 11-RES-JB
    11. 19312
    Prev
    Next
    INDEX
    Explanations

    percentages and numerical data related to financial markets and economics

    oai_token-act-pair · gpt-3.5-turbo

    financial performance metrics and percentage changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¦ãĤ¹
    -0.72
    pton
    -0.61
    ãģ¦
    -0.61
    ============
    -0.60
    natureconservancy
    -0.60
    ãĥ¯ãĥ³
    -0.59
    ãĤĮ
    -0.58
    ãĤ¤ãĥĪ
    -0.57
     proble
    -0.55
     tyrann
    -0.53
    POSITIVE LOGITS
     year
    0.97
     month
    0.82
     (-
    0.81
     quarter
    0.80
    ftime
    0.78
     compared
    0.77
    year
    0.77
     depreciation
    0.77
    bps
    0.77
     yen
    0.77
    Activations Density 0.080%

    No Known Activations