© 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. 11-RES-JB
    11. 9101
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and verbs related to recounting experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to origin or beginnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    padding
    -0.72
     distraction
    -0.71
     unfocusedRange
    -0.69
     glare
    -0.69
    limits
    -0.66
     distracting
    -0.66
    danger
    -0.65
    ħĭ
    -0.64
     inconvenience
    -0.64
    acceptable
    -0.63
    POSITIVE LOGITS
     originated
    1.60
     origins
    1.60
     genesis
    1.57
     origin
    1.56
     originate
    1.55
     beginnings
    1.52
     sprang
    1.38
     inception
    1.38
     earliest
    1.36
     arose
    1.28
    Activations Density 0.690%

    No Known Activations