© 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. 4-RES-JB
    11. 20783
    Prev
    Next
    INDEX
    Explanations

    references to actions or events happening simultaneously with another event

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "meanwhile" used as a transition in discourse

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

    No Comments

    Negative Logits
     hor
    -0.64
    viation
    -0.63
    manac
    -0.62
    gaard
    -0.60
    Vert
    -0.58
     THEM
    -0.58
     collection
    -0.58
     basket
    -0.57
    reason
    -0.56
     contribution
    -0.56
    POSITIVE LOGITS
     however
    0.85
     meanwhile
    0.78
    trak
    0.77
    zech
    0.74
     though
    0.71
    raints
    0.68
    inois
    0.68
    anamo
    0.66
    nown
    0.65
     although
    0.64
    Activations Density 0.177%

    No Known Activations