© 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. 6-RES-JB
    11. 17415
    Prev
    Next
    INDEX
    Explanations

    instances of the word "arrived at"

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to a specific point in time or location of arrival

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dared
    -0.67
     thirst
    -0.67
    fram
    -0.64
    kept
    -0.62
     dare
    -0.60
    lis
    -0.60
    criptions
    -0.59
     sourcing
    -0.59
    witch
    -0.58
    kered
    -0.58
    POSITIVE LOGITS
     shores
    0.90
     fruition
    0.81
     conclusions
    0.73
     conclusion
    0.71
     Arri
    0.69
     fray
    0.67
    INGTON
    0.66
    eport
    0.66
    ãĥ¯
    0.66
    estamp
    0.65
    Activations Density 0.096%

    No Known Activations