© 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. 12382
    Prev
    Next
    INDEX
    Explanations

    titles or names with a specific structure, potentially signaling news headlines or article headings

    oai_token-act-pair · gpt-3.5-turbo

    special characters and elements of formatting

    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
     disadvant
    -0.89
     unintended
    -0.80
     mathemat
    -0.79
     payday
    -0.78
     tremend
    -0.78
     contrace
    -0.76
     comprom
    -0.75
     loopholes
    -0.74
     buggy
    -0.74
     undermin
    -0.74
    POSITIVE LOGITS
    ï¸ı
    1.00
    é¾į
    0.95
    ï¸
    0.91
    tre
    0.89
    à¥
    0.86
    Joined
    0.84
    æľ
    0.83
    éĩ
    0.82
    ÙĦ
    0.79
    ship
    0.79
    Activations Density 0.493%

    No Known Activations