© 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. 4-RES-JB
    11. 3202
    Prev
    Next
    INDEX
    Explanations

    words related to a specific person named "ey."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Alexey."

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

    No Comments

    Negative Logits
    mint
    -0.78
    istani
    -0.77
    atoon
    -0.70
    atchewan
    -0.70
    ULAR
    -0.69
    dayName
    -0.68
    ACTED
    -0.63
    imen
    -0.63
     insomnia
    -0.63
    IFA
    -0.62
    POSITIVE LOGITS
    ewitness
    1.02
    ey
    0.90
    esy
    0.87
    ield
    0.81
    er
    0.80
    kj
    0.78
    giene
    0.77
    estinal
    0.77
    outube
    0.76
    eri
    0.73
    Activations Density 0.014%

    No Known Activations