© 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. 2995
    Prev
    Next
    INDEX
    Explanations

    phrases related to sequential events or ordering

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the word "one" followed by references to rankings or superlatives

    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
    heit
    -0.86
    ENCE
    -0.70
    oney
    -0.70
    âĢİ
    -0.69
    Change
    -0.68
    leeve
    -0.67
    ²
    -0.65
    Market
    -0.65
    ume
    -0.63
    otto
    -0.62
    POSITIVE LOGITS
     earliest
    0.93
     strang
    0.88
     largest
    0.86
     richest
    0.83
     busiest
    0.82
     oldest
    0.81
     aforementioned
    0.81
     finest
    0.81
     greatest
    0.81
     widest
    0.80
    Activations Density 0.098%

    No Known Activations