© 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. 2-RES-JB
    11. 9129
    Prev
    Next
    INDEX
    Explanations

    personal names or places with the string 'afa' or 'afi'

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ornament
    -0.71
    fish
    -0.67
    gram
    -0.66
     tease
    -0.66
    suit
    -0.65
    lines
    -0.64
    sight
    -0.62
     stitch
    -0.62
     anus
    -0.61
     Oath
    -0.61
    POSITIVE LOGITS
    afa
    1.03
    qua
    0.89
     Moroc
    0.79
    qs
    0.78
    yip
    0.77
    ortality
    0.76
    ////
    0.76
    ommod
    0.75
    ÄŁ
    0.75
     Pwr
    0.75
    Activations Density 0.017%

    No Known Activations