© 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. 1-RES-JB
    11. 4928
    Prev
    Next
    INDEX
    Explanations

    phrases written in a mix of different languages

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political structures and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RESULTS
    -0.49
    catentry
    -0.47
    DATA
    -0.47
    VIDEO
    -0.46
    NetMessage
    -0.45
    ugs
    -0.44
    ModLoader
    -0.43
    versely
    -0.42
    CDC
    -0.42
    ccording
    -0.42
    POSITIVE LOGITS
     --------------------
    0.54
    antes
    0.50
    ='
    0.47
    soDeliveryDate
    0.44
     eject
    0.43
    emonium
    0.42
    ="#
    0.42
    ensis
    0.41
     ell
    0.41
     CST
    0.41
    Activations Density 6.808%

    No Known Activations