Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 23555
    Prev
    Next
    INDEX
    Explanations

    words related to financial terms, particularly bankruptcy and insolvency

    oai_token-act-pair · gpt-3.5-turbo

    references to cycles, such as cyclical processes or patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FINE
    -0.72
     Grill
    -0.67
     graz
    -0.65
     independents
    -0.65
     corrid
    -0.63
     GOODMAN
    -0.62
     Saud
    -0.60
     Southwest
    -0.60
    én
    -0.59
     Forbidden
    -0.59
    POSITIVE LOGITS
    cy
    4.81
    cies
    2.01
    Cy
    1.90
     cy
    1.45
     Cy
    1.44
    cyl
    1.40
    ce
    1.35
    icy
    1.29
    ocy
    1.27
     CY
    1.26
    Activations Density 0.012%

    No Known Activations