© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 619
    Prev
    Next
    INDEX
    Explanations

    adjectives and nouns related to characters in a story, especially protagonists with a focus on their actions and traits

    oai_token-act-pair · gpt-3.5-turbo

    references to protagonists in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dos
    -0.91
    assic
    -0.84
    orks
    -0.78
    sterdam
    -0.76
    ensing
    -0.75
    iths
    -0.75
    itsch
    -0.72
    vor
    -0.71
    eln
    -0.70
    igree
    -0.69
    POSITIVE LOGITS
     protagonist
    1.17
     protagonists
    1.06
     heroine
    1.05
    acters
    0.99
     avatar
    0.77
     antagonist
    0.75
     unden
    0.70
     narrator
    0.69
     charact
    0.69
     Ethan
    0.68
    Activations Density 0.011%

    No Known Activations