© 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. 2-RES-JB
    11. 12702
    Prev
    Next
    INDEX
    Explanations

    mentions of light, bright, or glaring objects or events

    oai_token-act-pair · gpt-3.5-turbo

    references to flares and related terms, particularly in scientific or dramatic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesota
    -0.85
    ournal
    -0.81
    UFC
    -0.80
    esson
    -0.79
    */(
    -0.78
    rified
    -0.77
    HCR
    -0.76
    phis
    -0.75
    ordan
    -0.74
    ipeg
    -0.73
    POSITIVE LOGITS
     flares
    1.50
     flare
    1.40
     flared
    1.02
     eru
    0.90
     sparks
    0.83
    fires
    0.78
     empt
    0.76
     lamps
    0.74
    lights
    0.73
     bursts
    0.73
    Activations Density 0.005%

    No Known Activations