© 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. 2-RES-JB
    6. 17580
    Prev
    Next
    INDEX
    Explanations

    references to a specific word or phrase - "Aziz."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific place or entity, particularly referencing "Az."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     externalToEVAOnly
    -0.77
     Copenhagen
    -0.75
    çīĪ
    -0.71
    dfx
    -0.69
    mercial
    -0.68
    aceous
    -0.67
     Kepler
    -0.67
    CLASSIFIED
    -0.66
    nesday
    -0.66
    ACTED
    -0.65
    POSITIVE LOGITS
    azel
    1.22
    Az
    1.11
    tec
    1.08
     Az
    1.08
    eri
    0.96
    az
    0.88
    iz
    0.86
    bows
    0.86
    usa
    0.86
    aji
    0.86
    Activations Density 0.006%

    No Known Activations