© 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. 14855
    Prev
    Next
    INDEX
    Explanations

    instances where the word "Google" is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "go" and its variations in different 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
     Penet
    -0.70
     DRAG
    -0.69
     Peng
    -0.66
     COUR
    -0.64
     tract
    -0.63
    ãĥ¯ãĥ³
    -0.62
     Mane
    -0.61
     Tow
    -0.61
     Raz
    -0.61
    å°Ĩ
    -0.60
    POSITIVE LOGITS
    ettings
    0.89
    etime
    0.89
    lers
    0.88
    bles
    0.85
    merce
    0.84
    inite
    0.80
    oing
    0.79
    lies
    0.77
    anda
    0.76
    mit
    0.76
    Activations Density 0.070%

    No Known Activations