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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 21315
    Prev
    Next
    INDEX
    Explanations

    words related to the term "ee" and possibly names that contain it

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "being."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥķãĤ©
    -0.93
    ainer
    -0.83
    iques
    -0.76
    urgical
    -0.73
    iferation
    -0.69
    atform
    -0.68
    otine
    -0.68
    ique
    -0.66
    icken
    -0.65
    ĸļ
    -0.64
    POSITIVE LOGITS
    pee
    1.16
    ples
    1.00
    bling
    0.99
    zy
    0.96
    bies
    0.95
    bles
    0.95
    cham
    0.95
    UGE
    0.95
    rence
    0.94
    EEE
    0.94
    Activations Density 0.037%

    No Known Activations