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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 6394
    Prev
    Next
    INDEX
    Explanations

    words related to sources of light or illumination

    oai_token-act-pair · gpt-3.5-turbo

    references to lighting and illumination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    llah
    -0.69
    >[
    -0.65
    Relations
    -0.65
    ppo
    -0.64
    gress
    -0.63
    女
    -0.62
    çĶ°
    -0.62
    urdue
    -0.62
    Attempts
    -0.62
    ctive
    -0.62
    POSITIVE LOGITS
    pots
    1.09
     bulbs
    1.07
     bulb
    1.07
     lights
    1.04
    lights
    1.02
     lamps
    0.96
     torches
    0.96
    peed
    0.96
    creen
    0.95
     shone
    0.94
    Activations Density 0.015%

    No Known Activations