© 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. 15451
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific name related to crowdfunding or a game product

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific names or titles related to a particular game or project

    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
     compensation
    -0.71
     1911
    -0.69
     Higgins
    -0.66
     Hughes
    -0.64
     PDF
    -0.64
     Rs
    -0.62
     Dust
    -0.62
     Avalanche
    -0.61
     fit
    -0.61
     Loft
    -0.59
    POSITIVE LOGITS
    emon
    4.93
    emonic
    3.42
    amon
    1.59
    omon
    1.55
    emo
    1.29
    eton
    1.22
    emark
    1.13
    aimon
    1.13
    untu
    1.12
    imon
    1.11
    Activations Density 0.033%

    No Known Activations