© 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. 10-RES-JB
    11. 13897
    Prev
    Next
    INDEX
    Explanations

    compliments and positive feedback

    oai_token-act-pair · gpt-3.5-turbo

    mentions of personal attributes or opinions related to people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actionDate
    -0.73
    kefeller
    -0.66
     Mehran
    -0.66
     srfAttach
    -0.65
     lifelong
    -0.65
    ptive
    -0.64
    eros
    -0.60
    ordinary
    -0.59
    ¬¼
    -0.58
    女
    -0.57
    POSITIVE LOGITS
     seem
    1.37
     seems
    1.21
     seemed
    1.21
     mentioned
    1.01
     clearly
    0.99
     hinted
    0.98
     evidently
    0.97
     wisely
    0.97
     sounded
    0.94
     kindly
    0.94
    Activations Density 0.721%

    No Known Activations