© 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. 6-RES-JB
    6. 16893
    Prev
    Next
    INDEX
    Explanations

    phrases related to computer processes and commands

    oai_token-act-pair · gpt-3.5-turbo

    components and functions related to digital downloads and installations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otide
    -0.54
    Īè
    -0.53
    tek
    -0.52
    swer
    -0.52
    ukemia
    -0.52
    ãĤ¨
    -0.51
    ESA
    -0.51
    ellar
    -0.50
     architects
    -0.50
     Sons
    -0.49
    POSITIVE LOGITS
    itiveness
    0.59
    jri
    0.58
     Frenzy
    0.54
    ificantly
    0.54
    actory
    0.53
    anwhile
    0.53
    pees
    0.53
    alions
    0.52
    dam
    0.52
    adesh
    0.51
    Activations Density 0.879%

    No Known Activations