© 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. 12806
    Prev
    Next
    INDEX
    Explanations

    the name "Kamala" and its variants

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ala" and its variations in different contexts

    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
    lines
    -0.87
    line
    -0.86
    ly
    -0.86
    lies
    -0.85
    LY
    -0.84
    liness
    -0.83
    manship
    -0.83
    lessly
    -0.82
    dit
    -0.81
    lers
    -0.79
    POSITIVE LOGITS
    ibaba
    1.10
    uthor
    1.08
    emia
    1.04
     Pradesh
    0.95
    qua
    0.93
    isa
    0.89
    pha
    0.84
    velength
    0.83
    ensis
    0.83
    ala
    0.82
    Activations Density 0.018%

    No Known Activations