© 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. 3-RES-JB
    11. 5314
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "me" with a specific activation value of 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "me."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kefeller
    -0.85
    paralle
    -0.72
    iosity
    -0.68
     rage
    -0.67
    inyl
    -0.65
    tains
    -0.63
    raviolet
    -0.62
    EStreamFrame
    -0.62
     hierarch
    -0.61
     slic
    -0.61
    POSITIVE LOGITS
    asure
    1.28
    zzo
    1.18
    lda
    1.02
    adow
    1.01
    asured
    0.99
    adows
    0.99
    anwhile
    0.96
    asuring
    0.89
    ppo
    0.87
    isters
    0.85
    Activations Density 0.013%

    No Known Activations