© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 15141
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing characteristics or qualities

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions that emphasize connection or addition

    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
    zan
    -0.80
    DAY
    -0.80
    !--
    -0.76
    Wire
    -0.75
    cigarettes
    -0.70
    asking
    -0.68
    .--
    -0.68
    gets
    -0.68
    Lago
    -0.67
    -+-+
    -0.67
    POSITIVE LOGITS
     fraternity
    0.79
     fanbase
    0.76
     intric
    0.74
     mantle
    0.70
     community
    0.70
     genus
    0.69
     latent
    0.68
    ifice
    0.68
     aroma
    0.68
     possibilities
    0.67
    Activations Density 0.222%

    No Known Activations