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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 14690
    Prev
    Next
    INDEX
    Explanations

    Spanish and related words with the specific phonetic combination "ar" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ar" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¬¼
    -0.75
    e
    -0.66
    er
    -0.66
     depos
    -0.62
    ĸļ
    -0.61
    eur
    -0.60
     explan
    -0.59
    insula
    -0.57
    tons
    -0.56
    ĨĴ
    -0.56
    POSITIVE LOGITS
    riors
    1.07
    ashtra
    1.06
    ifle
    1.03
    thur
    1.03
    acter
    1.02
    vae
    1.02
    allel
    1.01
    raf
    0.98
    lington
    0.98
    ayan
    0.97
    Activations Density 0.071%

    No Known Activations