© 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. 4-RES-JB
    6. 20112
    Prev
    Next
    INDEX
    Explanations

    words related to specific names like 'Rupert', 'Gareth', and 'Clive'

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly Rupert Murdoch and Gareth

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

    No Comments

    Negative Logits
    ĺħ
    -0.90
    assian
    -0.78
    oÄŁ
    -0.75
    atchewan
    -0.75
    »Ĵ
    -0.74
    anza
    -0.71
    nesota
    -0.71
    atti
    -0.70
    wagen
    -0.69
    Ĥª
    -0.69
    POSITIVE LOGITS
     Murdoch
    0.83
     Giles
    0.79
    wcs
    0.75
     Gareth
    0.75
     Rupert
    0.74
    ESCO
    0.71
    Bey
    0.70
     Kelvin
    0.70
     Coke
    0.68
     Orwell
    0.68
    Activations Density 0.024%

    No Known Activations