© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 15612
    Prev
    Next
    INDEX
    Explanations

    words related to shadows

    oai_token-act-pair · gpt-3.5-turbo

    references to "shadow" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Frequ
    -0.75
    pps
    -0.70
    atl
    -0.68
     Spears
    -0.67
     Alc
    -0.66
    Ott
    -0.66
    ific
    -0.66
    ALLY
    -0.66
    ichi
    -0.66
    HF
    -0.65
    POSITIVE LOGITS
     shadow
    3.90
     shadows
    2.61
    Shadow
    2.52
     Shadow
    2.45
    shadow
    2.28
     Shadows
    1.69
     shadowy
    1.49
     shade
    1.37
     twilight
    1.35
     ghost
    1.21
    Activations Density 0.004%

    No Known Activations