© 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. 6-RES-JB
    11. 2845
    Prev
    Next
    INDEX
    Explanations

    names related to geographical locations and legal terms

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to geographical locations and political entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Phys
    -0.88
    ãĤ´ãĥ³
    -0.79
    ĸļ
    -0.78
     Wally
    -0.77
    isSpecialOrderable
    -0.76
    Pitt
    -0.73
     Grateful
    -0.73
     Cthulhu
    -0.72
    Wheel
    -0.72
    Nut
    -0.68
    POSITIVE LOGITS
    atan
    0.94
     annexed
    0.90
    ifa
    0.83
     unpop
    0.79
     citiz
    0.78
    istani
    0.76
     Georgian
    0.76
     Caucasus
    0.75
     Cyprus
    0.75
     deval
    0.75
    Activations Density 0.326%

    No Known Activations