© 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. 8950
    Prev
    Next
    INDEX
    Explanations

    phrases or abbreviations related to specific organizations or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental or administrative departments

    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
    packing
    -0.75
    ments
    -0.71
    sets
    -0.69
     Dragonbound
    -0.69
    erous
    -0.68
    deck
    -0.68
    lander
    -0.67
    ties
    -0.67
    achu
    -0.66
    naires
    -0.66
    POSITIVE LOGITS
    ILY
    1.34
    VID
    1.11
    BLE
    1.00
    VIS
    0.90
    hyde
    0.89
    WN
    0.88
    ZZ
    0.88
    VE
    0.88
    OTA
    0.86
    pling
    0.84
    Activations Density 0.028%

    No Known Activations