© 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. 8-RES-JB
    11. 22285
    Prev
    Next
    INDEX
    Explanations

    references to the term "Lone" or similar isolated and singular entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "lone" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yrinth
    -0.86
    blance
    -0.86
    ilic
    -0.84
    ilation
    -0.83
    rador
    -0.81
    encies
    -0.79
    lain
    -0.78
    ropri
    -0.77
    owder
    -0.75
    ulative
    -0.75
    POSITIVE LOGITS
     wolf
    0.80
    \\\\\\\\
    0.76
    hua
    0.69
     deer
    0.68
    eteen
    0.68
     Bale
    0.68
    \\\\
    0.67
     fide
    0.66
     wolves
    0.66
    jas
    0.65
    Activations Density 0.097%

    No Known Activations