© 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 EvalsExportsinterp-engineNEWAPI 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. 5563
    Prev
    Next
    INDEX
    Explanations

    names or variations of the name "Ani"

    oai_token-act-pair · gpt-3.5-turbo

    names or terms that have the phonetic pattern "ani", "ari", or related vowel combinations

    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
    spin
    -0.80
    lain
    -0.79
    ting
    -0.77
    ted
    -0.75
    liest
    -0.74
    theless
    -0.71
    phe
    -0.69
    tons
    -0.67
    tone
    -0.65
    size
    -0.65
    POSITIVE LOGITS
    Äĩ
    1.69
    ya
    1.56
    yah
    1.52
    ère
    1.36
    emi
    1.31
    ye
    1.21
    yan
    1.17
    ño
    1.13
    Äį
    1.09
    qa
    1.05
    Activations Density 0.162%

    No Known Activations