© 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. 14504
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons or contrasts

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "the."

    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
    arate
    -0.79
    antes
    -0.79
    Ò
    -0.77
    imi
    -0.76
    thood
    -0.75
    ceive
    -0.73
    icia
    -0.72
    bg
    -0.71
    arettes
    -0.71
    ania
    -0.71
    POSITIVE LOGITS
     latter
    1.30
     biggest
    1.21
     vast
    1.19
     majority
    1.16
     sheer
    1.14
     simplest
    1.12
     absence
    1.10
     slightest
    1.10
     latest
    1.09
    oret
    1.08
    Activations Density 0.357%

    No Known Activations