© 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. 9-RES-JB
    11. 5489
    Prev
    Next
    INDEX
    Explanations

    phrases related to missed opportunities or regrets

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements regarding past actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inki
    -0.73
    apeshifter
    -0.71
    ema
    -0.66
    UGC
    -0.64
     denotes
    -0.61
    interstitial
    -0.59
    Ê
    -0.59
     NCT
    -0.58
    onymous
    -0.56
    enum
    -0.56
    POSITIVE LOGITS
     sooner
    1.32
     earlier
    0.89
     wiser
    0.88
     Ago
    0.82
    Had
    0.76
     differently
    0.74
     nicer
    0.74
     clearer
    0.73
    better
    0.73
     quicker
    0.72
    Activations Density 0.433%

    No Known Activations