© 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. 2-RES-JB
    11. 11337
    Prev
    Next
    INDEX
    Explanations

    financial terms or abbreviations related to financial analysis

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific organization or publication, particularly associated with the acronym "EW" and other acronyms related to emotional intelligence (EQ)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abad
    -0.85
    tera
    -0.73
    adic
    -0.65
     Santana
    -0.63
    soon
    -0.63
     citation
    -0.62
     Serbian
    -0.62
    iasis
    -0.61
    arial
    -0.61
    ured
    -0.60
    POSITIVE LOGITS
    estern
    1.15
    ITNESS
    1.04
    ORK
    1.00
     EW
    0.99
    TN
    0.93
    OW
    0.92
    EW
    0.92
    restling
    0.92
    ATER
    0.91
    LIN
    0.91
    Activations Density 0.011%

    No Known Activations