© 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. 20903
    Prev
    Next
    INDEX
    Explanations

    the word "shadow" followed by another word

    oai_token-act-pair · gpt-3.5-turbo

    references to "shadow" roles in a political context

    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
    urses
    -0.86
    artney
    -0.85
    anchester
    -0.85
    ickr
    -0.83
    keye
    -0.79
    awaru
    -0.78
    renheit
    -0.76
    otide
    -0.76
    ourse
    -0.71
    ancock
    -0.71
    POSITIVE LOGITS
    moon
    1.02
    boxing
    0.97
    flame
    0.89
    loo
    0.86
    runners
    0.83
    hawk
    0.81
    shadow
    0.80
     Shadow
    0.80
     shadow
    0.76
    lights
    0.76
    Activations Density 0.025%

    No Known Activations