© 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. 11304
    Prev
    Next
    INDEX
    Explanations

    phrases related to fulfilling goals or purposes

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "the" to determine emphasis or significance in context

    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
     besides
    -0.84
    abouts
    -0.80
     namely
    -0.79
     beforehand
    -0.76
    !!!!
    -0.76
     alone
    -0.75
    NULL
    -0.73
     wherein
    -0.72
    live
    -0.71
     whereby
    -0.70
    POSITIVE LOGITS
     tenets
    1.21
     sentiments
    1.14
     realities
    1.14
     sensibilities
    1.11
     complexities
    1.10
     spirit
    1.08
     ideals
    1.08
     virtues
    1.07
     principles
    1.06
     ethos
    1.04
    Activations Density 0.296%

    No Known Activations