© 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. 6-RES-JB
    11. 7311
    Prev
    Next
    INDEX
    Explanations

    phrases related to revealing or bringing something into view

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "to light," particularly in contexts related to revealing information or discoveries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     apologize
    -0.71
    apons
    -0.70
    okia
    -0.70
     Rampage
    -0.70
    ettings
    -0.69
    regor
    -0.68
    iquid
    -0.67
    ocide
    -0.67
     apologise
    -0.66
    Dur
    -0.66
    POSITIVE LOGITS
    enment
    1.07
    weights
    1.06
    lights
    0.98
    ener
    0.93
    hearted
    0.89
    eners
    0.88
     bulb
    0.88
    ening
    0.87
     shone
    0.85
     shine
    0.84
    Activations Density 0.021%

    No Known Activations