© 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. 1-RES-JB
    11. 21015
    Prev
    Next
    INDEX
    Explanations

    phrases related to visual blurriness

    oai_token-act-pair · gpt-3.5-turbo

    references to lack of clarity or indistinctness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itutional
    -0.92
    ept
    -0.86
    EEK
    -0.78
    ablishment
    -0.77
    emet
    -0.76
    ETH
    -0.74
    essee
    -0.71
    areth
    -0.70
    ereo
    -0.69
    eanor
    -0.68
    POSITIVE LOGITS
     blur
    1.41
     blurred
    1.00
    iform
    0.81
     blurry
    0.76
     blending
    0.72
     scattering
    0.71
    ected
    0.70
    lag
    0.69
    rier
    0.68
    balls
    0.67
    Activations Density 0.007%

    No Known Activations