© 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. 0-RES-JB
    11. 4836
    Prev
    Next
    INDEX
    Explanations

    Russian words related to music and performance

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of a specific character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Oaks
    -0.64
     mount
    -0.62
     hinge
    -0.62
     holiest
    -0.62
    backs
    -0.62
     Wat
    -0.61
     tall
    -0.61
     supreme
    -0.60
     swift
    -0.60
     recall
    -0.59
    POSITIVE LOGITS
    и
    3.96
    оÐ
    2.56
    Ñĭ
    2.51
    о
    2.50
    а
    2.46
    Ñĥ
    2.32
    е
    2.30
    ÑĮ
    2.22
    Ñı
    2.13
    к
    1.91
    Activations Density 0.006%

    No Known Activations