© 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. 10-RES-JB
    11. 2751
    Prev
    Next
    INDEX
    Explanations

    text related to narrative elements

    oai_token-act-pair · gpt-3.5-turbo

    elements related to narrative structure and thematic content in story analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     priceless
    -0.77
     Row
    -0.76
    Gall
    -0.72
    Wow
    -0.71
    Awesome
    -0.70
    Got
    -0.70
     Volcano
    -0.67
     Illegal
    -0.66
    Magikarp
    -0.65
    Happy
    -0.65
    POSITIVE LOGITS
     esche
    1.60
     focuses
    1.54
     emphasizes
    1.42
     relies
    1.38
     foc
    1.35
     seeks
    1.30
     presupp
    1.29
     aims
    1.29
     incorporates
    1.27
     emphas
    1.26
    Activations Density 0.410%

    No Known Activations