© 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. 1164
    Prev
    Next
    INDEX
    Explanations

    phrases relating to governmental entities like national archives, town councils, and political parties

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and various proper nouns

    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
    days
    -0.77
     beforehand
    -0.76
    actively
    -0.68
    agree
    -0.67
    edi
    -0.67
     without
    -0.66
    species
    -0.66
    Filename
    -0.66
    seekers
    -0.64
    either
    -0.64
    POSITIVE LOGITS
     rest
    0.86
     remainder
    0.81
     occasional
    0.81
     aforementioned
    0.80
     entirety
    0.80
     consequ
    0.78
     corresponding
    0.75
     entire
    0.75
     resultant
    0.73
     Flavoring
    0.70
    Activations Density 0.333%

    No Known Activations