© 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. 3-RES-JB
    11. 13085
    Prev
    Next
    INDEX
    Explanations

    references to friends or companions

    oai_token-act-pair · gpt-3.5-turbo

    references to friends or close companions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apers
    -0.83
    encers
    -0.79
    ined
    -0.78
    pite
    -0.77
    aders
    -0.76
    utenberg
    -0.75
    Analysis
    -0.75
    ainer
    -0.75
    inem
    -0.73
    orius
    -0.73
    POSITIVE LOGITS
     buddy
    1.29
     buddies
    1.15
     Buddy
    0.91
     Holly
    0.83
     Louie
    0.79
     Bud
    0.76
    gie
    0.76
     pals
    0.76
    busters
    0.71
     Faw
    0.70
    Activations Density 0.007%

    No Known Activations