© 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. 11871
    Prev
    Next
    INDEX
    Explanations

    words with the letter sequence "eth" followed by a single character or space

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "e" in various forms

    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
     slot
    -0.69
     Malays
    -0.66
     propensity
    -0.64
     ditch
    -0.61
     detail
    -0.60
     foss
    -0.59
     fragmentation
    -0.57
    ashtra
    -0.56
     directions
    -0.56
     tremend
    -0.56
    POSITIVE LOGITS
    lehem
    0.98
    zeb
    0.93
    qt
    0.86
    iful
    0.85
    aign
    0.82
    avior
    0.79
    eat
    0.74
    leck
    0.73
    mingham
    0.73
    ulf
    0.73
    Activations Density 0.068%

    No Known Activations