© 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. 20583
    Prev
    Next
    INDEX
    Explanations

    phrases related to conclusions or dramatic events, often suggesting finality or significant changes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the concept of an ending or conclusion

    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
    BLIC
    -0.80
     Aure
    -0.69
    agine
    -0.65
    pell
    -0.63
     bund
    -0.60
     INTO
    -0.59
     outgoing
    -0.59
     unders
    -0.59
    dinand
    -0.58
     Hera
    -0.56
    POSITIVE LOGITS
    angering
    1.27
    owment
    1.19
    orph
    1.12
    game
    1.12
    earing
    1.09
    angered
    1.08
    angers
    1.03
    ocrine
    1.00
    eared
    1.00
    ocrin
    0.95
    Activations Density 0.037%

    No Known Activations