© 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. 788
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a state of being or action that occurred in the past

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "been" indicating a continuous or completed action

    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
    izable
    -0.74
    erity
    -0.67
    now
    -0.65
     VIDEOS
    -0.65
    essee
    -0.64
    Today
    -0.63
     certs
    -0.63
    today
    -0.63
     simultane
    -0.61
    orial
    -0.61
    POSITIVE LOGITS
     previously
    0.96
     warned
    0.94
     dormant
    0.94
     ordered
    0.90
     subjected
    0.88
     expelled
    0.87
     briefed
    0.87
     instructed
    0.87
     misled
    0.86
     kicked
    0.86
    Activations Density 0.089%

    No Known Activations