© 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. 13553
    Prev
    Next
    INDEX
    Explanations

    mentions of significant aspects or developments

    oai_token-act-pair · gpt-3.5-turbo

    phrases or constructs that involve the word "the" and highlight significant features or characteristics

    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
    ago
    -0.79
    hei
    -0.74
    hops
    -0.71
    ho
    -0.69
    airs
    -0.69
    SEA
    -0.68
    aho
    -0.68
    fw
    -0.68
    ishers
    -0.67
    γ
    -0.67
    POSITIVE LOGITS
     slightest
    1.03
     inability
    1.00
     sheer
    0.99
     emergence
    0.98
     presence
    0.93
     extent
    0.89
     tendency
    0.88
     lack
    0.88
     possibility
    0.87
     resultant
    0.86
    Activations Density 0.147%

    No Known Activations