© 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. 1-RES-JB
    11. 14386
    Prev
    Next
    INDEX
    Explanations

    words related to ongoing or continuous actions or events

    oai_token-act-pair · gpt-3.5-turbo

    references to ongoing activities or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingers
    -0.85
    ppers
    -0.81
    yer
    -0.79
    pper
    -0.79
    acho
    -0.78
    istics
    -0.73
    inger
    -0.72
    olog
    -0.71
    iasis
    -0.70
    oak
    -0.69
    POSITIVE LOGITS
     ongoing
    1.28
     developments
    0.96
     unresolved
    0.95
     deliberations
    0.90
     investigations
    0.89
     saga
    0.86
     underway
    0.86
     discussions
    0.83
     investigation
    0.83
     unfolding
    0.82
    Activations Density 0.009%

    No Known Activations