© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 1760
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "pale"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "pale" 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 @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Assembly
    -0.77
    çīĪ
    -0.72
    IVERS
    -0.67
    Applications
    -0.64
    ually
    -0.63
    hips
    -0.63
     defe
    -0.63
    rael
    -0.62
    NRS
    -0.62
    Upgrade
    -0.62
    POSITIVE LOGITS
    olithic
    1.48
    ozo
    1.08
    ogram
    0.95
    croft
    0.95
    rose
    0.93
    ographic
    0.92
    ohyd
    0.91
    ocl
    0.89
     complexion
    0.87
    opath
    0.85
    Activations Density 0.032%

    No Known Activations