© 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. 74
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases related to conveying or representing information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "convey" and its variants in various contexts

    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
     Leone
    -0.68
    chens
    -0.68
    scill
    -0.67
    ches
    -0.66
     shalt
    -0.65
    ADE
    -0.64
    bre
    -0.62
     Bav
    -0.61
    FE
    -0.61
     scene
    -0.61
    POSITIVE LOGITS
     conveyed
    0.90
    cha
    0.79
    ively
    0.77
    ances
    0.75
     convey
    0.75
    sheets
    0.75
    ance
    0.74
    ragon
    0.74
    uron
    0.73
    engers
    0.72
    Activations Density 0.012%

    No Known Activations