© 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. 20558
    Prev
    Next
    INDEX
    Explanations

    passages discussing statistical or factual information

    oai_token-act-pair · gpt-3.5-turbo

    references to the verb "been" indicating ongoing states or conditions

    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
    anges
    -0.76
    Profile
    -0.75
    soon
    -0.64
     Later
    -0.64
    terday
    -0.63
     Hert
    -0.63
     Wid
    -0.63
    now
    -0.62
    Must
    -0.61
    later
    -0.60
    POSITIVE LOGITS
     hijacked
    0.89
     steadily
    0.88
     relegated
    0.87
     forgotten
    0.84
     overshadowed
    0.84
     likened
    0.83
     fruitful
    0.82
     eroded
    0.81
    cffffcc
    0.80
     proven
    0.80
    Activations Density 0.130%

    No Known Activations