© 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. 7825
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical movement or gestures involving interaction with others

    oai_token-act-pair · gpt-3.5-turbo

    instances of invitation or arrival

    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
    nesota
    -0.72
    ©¶æ
    -0.68
    ãĥ¯ãĥ³
    -0.68
    hemy
    -0.66
    ģĸ
    -0.64
    ãĤ©
    -0.64
    ¶ħ
    -0.63
     PID
    -0.63
    imov
    -0.62
    ĪĴ
    -0.61
    POSITIVE LOGITS
     town
    0.85
     anytime
    0.85
     expecting
    0.81
     hither
    0.80
     smelling
    0.77
     tonight
    0.77
     sidx
    0.76
     voluntarily
    0.74
     here
    0.74
     visit
    0.73
    Activations Density 0.210%

    No Known Activations