© 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. 4-RES-JB
    11. 16739
    Prev
    Next
    INDEX
    Explanations

    words related to prototypes and protests

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Prot" and its variations, likely related to protocols or protections

    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
    manship
    -0.81
    hyde
    -0.75
    uliffe
    -0.75
    INESS
    -0.72
    Ļ½
    -0.69
     hay
    -0.68
    è£ħ
    -0.67
     Sins
    -0.67
    ãĤ¼ãĤ¦ãĤ¹
    -0.67
    hips
    -0.66
    POSITIVE LOGITS
    agonist
    1.33
    otyp
    1.33
    otypes
    1.28
    ected
    1.24
    ests
    1.13
    ocol
    1.08
    agonists
    1.04
    otype
    0.99
    racted
    0.97
    ection
    0.93
    Activations Density 0.015%

    No Known Activations