© 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. 4275
    Prev
    Next
    INDEX
    Explanations

    proper names and locations related to Johannes, Jae, Cologne, Viridian Capital, India, and China

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names and locations, particularly focusing on the names "Johannes" and "Cologne"

    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
    holders
    -1.04
    holder
    -0.81
     gulf
    -0.78
    »Ĵ
    -0.75
    ĺħ
    -0.75
    tackle
    -0.68
    ahon
    -0.67
    tons
    -0.65
    uten
    -0.65
    uyomi
    -0.65
    POSITIVE LOGITS
     Kepler
    0.97
    gil
    0.90
    ansson
    0.88
     Gutenberg
    0.83
     Johannes
    0.81
    NEY
    0.80
    CLE
    0.78
    seys
    0.74
    berto
    0.70
     Durham
    0.70
    Activations Density 0.023%

    No Known Activations