© 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. 3-RES-JB
    11. 6041
    Prev
    Next
    INDEX
    Explanations

    countries or places, particularly Estonia

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Estonia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enthal
    -0.83
    esses
    -0.81
    izations
    -0.73
    enger
    -0.71
    itiz
    -0.71
    arters
    -0.70
    guard
    -0.70
    ity
    -0.70
    erd
    -0.69
    ebus
    -0.67
    POSITIVE LOGITS
    oral
    0.95
    anium
    0.79
    orescence
    0.75
    rix
    0.72
    urity
    0.72
    ople
    0.71
    clave
    0.70
    forth
    0.68
    olkien
    0.67
    rics
    0.66
    Activations Density 0.028%

    No Known Activations