© 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. 7-RES-JB
    11. 2225
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'Limelight'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Lim" and its variations, suggesting a focus on references to a specific person or entity associated with that name

    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
    ALK
    -0.72
     Wisconsin
    -0.64
     Pact
    -0.63
     Forsaken
    -0.61
     Allies
    -0.60
     Vald
    -0.59
    Ò
    -0.59
     Slave
    -0.58
    WR
    -0.58
    washer
    -0.58
    POSITIVE LOGITS
    elight
    1.26
    itations
    1.20
    erick
    1.16
    ogy
    1.12
    bered
    1.02
    iter
    1.00
    inished
    0.98
    psons
    0.96
    bers
    0.95
    estone
    0.94
    Activations Density 0.020%

    No Known Activations