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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 19088
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of 'ey' in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ey."

    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
    mint
    -0.84
    istani
    -0.81
    ULAR
    -0.76
    IENT
    -0.70
    atoon
    -0.68
    ivity
    -0.66
    ifiable
    -0.64
    imens
    -0.63
    ãĥķãĤ©
    -0.62
    adium
    -0.62
    POSITIVE LOGITS
    ewitness
    1.09
    kj
    0.99
    ield
    0.77
    outube
    0.77
    oshi
    0.76
    er
    0.75
    giene
    0.75
     Myster
    0.75
    usha
    0.73
    ipel
    0.73
    Activations Density 0.039%

    No Known Activations