© 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. 23674
    Prev
    Next
    INDEX
    Explanations

    phrases related to common storytelling tropes and clichés

    oai_token-act-pair · gpt-3.5-turbo

    terms related to narrative tropes and clichés

    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
    gur
    -0.90
    hand
    -0.72
    brew
    -0.71
    ilated
    -0.70
     trials
    -0.69
     Ethiopian
    -0.69
    gan
    -0.68
    vals
    -0.68
    ander
    -0.66
    imentary
    -0.66
    POSITIVE LOGITS
    pmwiki
    1.35
     trope
    1.26
     tropes
    1.14
    enegger
    0.87
     clich
    0.86
     invoked
    0.77
    witz
    0.77
    OPLE
    0.73
    -+-+
    0.69
     spelled
    0.67
    Activations Density 0.025%

    No Known Activations