© 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. 4-RES-JB
    11. 4247
    Prev
    Next
    INDEX
    Explanations

    references to physical light or objects that are light in weight

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "light" in various contexts

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

    No Comments

    Negative Logits
    halla
    -0.92
    ettings
    -0.86
    apons
    -0.73
    OPLE
    -0.73
    OUP
    -0.72
     Bagg
    -0.69
    ij士
    -0.69
    ä½ľ
    -0.68
    isner
    -0.68
     Fas
    -0.68
    POSITIVE LOGITS
     bulb
    1.21
    hearted
    1.16
    bul
    1.11
    weights
    1.11
    ening
    1.10
     bulbs
    1.08
    enment
    1.04
    lights
    1.03
    heartedly
    1.00
    bringer
    0.95
    Activations Density 0.023%

    No Known Activations