© 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. 20017
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a comparison or context based on a specific situation or information

    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
    remlin
    -0.84
     Legisl
    -0.79
     Merrill
    -0.78
    atars
    -0.73
    HCR
    -0.73
    Russ
    -0.71
    apego
    -0.69
    JUST
    -0.68
    pload
    -0.68
     McMaster
    -0.68
    POSITIVE LOGITS
     bulb
    1.07
    enment
    1.06
    weights
    0.99
     bulbs
    0.96
    ening
    0.96
    lights
    0.90
    hearted
    0.86
    ened
    0.83
    eners
    0.80
    heartedly
    0.78
    Activations Density 0.009%

    No Known Activations