© 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. 10684
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific research and experimental results

    oai_token-act-pair · gpt-3.5-turbo

    references to outcomes or findings

    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
    resent
    -0.71
    yne
    -0.66
     Passage
    -0.65
     vigil
    -0.65
     actionGroup
    -0.61
     rainy
    -0.61
     vows
    -0.59
     maj
    -0.59
     capital
    -0.58
    kov
    -0.57
    POSITIVE LOGITS
    results
    0.91
     results
    0.88
    iments
    0.85
     Results
    0.81
    iveness
    0.80
    Results
    0.79
    ĸļ
    0.76
    ample
    0.74
    Panel
    0.73
    amples
    0.73
    Activations Density 0.019%

    No Known Activations