© 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. 5190
    Prev
    Next
    INDEX
    Explanations

    instances where something has been accomplished or achieved after a period of time

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to achieving goals or reaching a sense of completion

    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
     constantly
    -0.86
     frequently
    -0.78
     continually
    -0.69
     rarely
    -0.69
    often
    -0.68
     seldom
    -0.68
     inefficient
    -0.68
     never
    -0.67
    always
    -0.67
     disproportionately
    -0.66
    POSITIVE LOGITS
     realization
    1.04
    enough
    0.95
     reckoning
    0.95
    Enough
    0.90
    iphany
    0.89
     sanity
    0.87
     semblance
    0.84
     fruition
    0.84
     acknowledgement
    0.81
     grasp
    0.81
    Activations Density 0.495%

    No Known Activations