© 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
    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. 22247
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "sey."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Sey" or related variations thereof

    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
     tense
    -0.70
    endar
    -0.68
    agonist
    -0.68
     pity
    -0.66
    acity
    -0.66
     analges
    -0.66
    aciously
    -0.65
     ammo
    -0.64
    HAHAHAHA
    -0.64
    ACTED
    -0.64
    POSITIVE LOGITS
    sey
    1.11
    eah
    0.82
    yk
    0.81
    onduct
    0.80
    pur
    0.78
     Payton
    0.78
    ez
    0.77
    bones
    0.76
    bone
    0.75
     Stevenson
    0.75
    Activations Density 0.010%

    No Known Activations