© 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. 17301
    Prev
    Next
    INDEX
    Explanations

    words related to the composer Shostakovich

    oai_token-act-pair · gpt-3.5-turbo

    names associated with specific individuals, particularly those ending in 'ovich' or 'vich'

    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
    ologies
    -0.88
    culated
    -0.72
    ologically
    -0.68
    meet
    -0.64
    pled
    -0.64
    adian
    -0.62
    printed
    -0.60
     unsuspecting
    -0.60
    itiveness
    -0.60
    ĻĤ
    -0.57
    POSITIVE LOGITS
    ovich
    0.93
    sburg
    0.93
    ONSORED
    0.92
    ski
    0.92
    è£ħ
    0.88
    ota
    0.77
    wine
    0.75
    ansk
    0.74
    irus
    0.74
     III
    0.71
    Activations Density 0.008%

    No Known Activations