© 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. 9-RES-JB
    11. 7423
    Prev
    Next
    INDEX
    Explanations

    news headlines with the phrase "has announced."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "has" and its variants in statements relating to actions or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    seless
    -0.65
    eem
    -0.65
    jam
    -0.63
    soDeliveryDate
    -0.62
    ecd
    -0.61
    ti
    -0.58
    ItemThumbnailImage
    -0.58
     Apart
    -0.58
    Newsletter
    -0.57
    raw
    -0.56
    POSITIVE LOGITS
     been
    1.29
     begun
    1.17
     undergone
    1.15
     become
    1.14
     emerged
    1.12
    been
    1.09
     teamed
    1.05
     embarked
    1.04
     arrived
    1.00
     finally
    0.99
    Activations Density 0.232%

    No Known Activations