© 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. 6-RES-JB
    11. 12872
    Prev
    Next
    INDEX
    Explanations

    strings with a special symbol followed by numbers, often indicating specific instructions or commands

    oai_token-act-pair · gpt-3.5-turbo

    symbols or special characters found in technical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     semblance
    -0.74
     federation
    -0.71
     distraction
    -0.70
     shroud
    -0.69
     fragmentation
    -0.69
     Ukrain
    -0.69
     destro
    -0.68
     interfering
    -0.68
     rewriting
    -0.67
    iewicz
    -0.67
    POSITIVE LOGITS
    ł
    1.14
    ª
    1.11
    ¹
    1.10
    ij
    1.06
    £
    1.04
    IJ
    1.02
    Ĵ
    0.98
    ı
    0.96
    į
    0.96
    »
    0.95
    Activations Density 0.192%

    No Known Activations