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

    Neuronpedia

    Jacobian LensNEW
    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. 7921
    Prev
    Next
    INDEX
    Explanations

    instances where something is replaced or done differently than expected

    oai_token-act-pair · gpt-3.5-turbo

    instances of contrast or an alternative perspective being introduced

    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
    emate
    -0.62
    andestine
    -0.62
    oran
    -0.58
    eria
    -0.57
     Flavoring
    -0.56
     Nev
    -0.56
    AG
    -0.56
     Calif
    -0.55
     Wash
    -0.55
    nce
    -0.55
    POSITIVE LOGITS
    Ļ½
    0.74
    ":"/
    0.71
    roman
    0.69
     opt
    0.68
     succumb
    0.67
     relied
    0.66
     chose
    0.65
     opting
    0.65
    ocus
    0.64
    «ĺ
    0.63
    Activations Density 0.019%

    No Known Activations