© 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. 10-RES-JB
    11. 13885
    Prev
    Next
    INDEX
    Explanations

    phrases indicating storytelling or narration

    oai_token-act-pair · gpt-3.5-turbo

    verbs that communicate the act of conveying information or stories

    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
    adesh
    -0.77
    icut
    -0.73
    intend
    -0.67
    ternity
    -0.66
     ILCS
    -0.65
    aband
    -0.65
    ican
    -0.64
    Corp
    -0.63
    igslist
    -0.62
    pac
    -0.62
    POSITIVE LOGITS
     us
    1.34
    tale
    1.26
     tales
    1.12
     stories
    1.07
     me
    0.97
     viewers
    0.94
    ingly
    0.92
     tale
    0.91
     jokes
    0.90
     Tale
    0.90
    Activations Density 0.070%

    No Known Activations