© 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. 2836
    Prev
    Next
    INDEX
    Explanations

    phrases comparing or describing similarities with a specific subject

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference comparisons or analogies, particularly focusing on the word "those."

    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
     Grac
    -0.64
     pause
    -0.62
     Hes
    -0.59
     Karn
    -0.56
     Count
    -0.55
     Cec
    -0.55
    Second
    -0.54
     Wrestle
    -0.54
    adier
    -0.53
    EMENT
    -0.53
    POSITIVE LOGITS
    usual
    0.80
     describ
    0.80
     usual
    0.75
     prevailing
    0.75
     confir
    0.71
    hots
    0.70
     recip
    0.69
     sket
    0.67
     estab
    0.67
    typ
    0.67
    Activations Density 0.084%

    No Known Activations