© 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. 21171
    Prev
    Next
    INDEX
    Explanations

    specific words, typically involving locations or titles with 'ess', 'il', 'ri', 'dale', 'ika', or 'aw' in them

    oai_token-act-pair · gpt-3.5-turbo

    specific names, labels, and terms commonly associated with places or landmarks

    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
    xual
    -0.78
    oday
    -0.68
    ĸļ
    -0.67
    uncture
    -0.67
    ËĪ
    -0.65
    oku
    -0.63
    pring
    -0.62
    BILITIES
    -0.60
     whistle
    -0.60
     thor
    -0.60
    POSITIVE LOGITS
    ruary
    0.89
    arlane
    0.82
    tein
    0.79
    illet
    0.77
    phia
    0.72
    levard
    0.66
    eger
    0.61
     Corpus
    0.61
    igating
    0.61
    igate
    0.60
    Activations Density 0.212%

    No Known Activations