© 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. 12903
    Prev
    Next
    INDEX
    Explanations

    superlatives indicating excellence or superiority

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote superiority or excellence

    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
    idon
    -0.86
    mitting
    -0.78
    ustom
    -0.77
    ategory
    -0.72
    zanne
    -0.72
    chy
    -0.68
    clair
    -0.66
    sten
    -0.65
    reon
    -0.64
    aton
    -0.64
    POSITIVE LOGITS
    seller
    1.26
    iary
    0.95
     predictor
    0.86
     possible
    0.84
     behaved
    0.82
    sell
    0.81
     suited
    0.79
     compliment
    0.74
     exempl
    0.74
     exponent
    0.73
    Activations Density 0.044%

    No Known Activations