© 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. 4-RES-JB
    11. 10419
    Prev
    Next
    INDEX
    Explanations

    names of persons or entities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names

    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
    ODUCT
    -0.75
    Ó
    -0.72
    eur
    -0.71
    chnology
    -0.70
    MENT
    -0.70
     Closed
    -0.69
    ttes
    -0.68
     Portsmouth
    -0.68
     HMS
    -0.64
     Mysterious
    -0.64
    POSITIVE LOGITS
    zai
    1.06
    iyah
    1.02
     Ahmad
    0.98
    idia
    0.89
    uates
    0.89
    abad
    0.87
    kson
    0.84
    ifa
    0.83
    abi
    0.80
    iating
    0.80
    Activations Density 0.009%

    No Known Activations