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

    Neuronpedia

    APICircuit 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. 19590
    Prev
    Next
    INDEX
    Explanations

    keywords related to criticality or urgency

    oai_token-act-pair · gpt-3.5-turbo

    terms related to critical analysis and leadership contexts

    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
     pim
    -0.76
     monop
    -0.73
    ¸
    -0.69
     Aviv
    -0.68
    wana
    -0.67
     pocket
    -0.64
    gom
    -0.64
     wage
    -0.63
     sadd
    -0.62
     selfish
    -0.61
    POSITIVE LOGITS
    Critical
    2.31
     Critical
    2.28
    critical
    2.19
     Syri
    1.68
     Leadership
    1.28
     EDT
    1.24
     Minor
    0.98
     Frankfurt
    0.96
    ritical
    0.95
     Columb
    0.88
    Activations Density 0.044%

    No Known Activations