© 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. 8-RES-JB
    11. 1284
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the likelihood or potential of future events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating expectations or predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guessing
    -0.82
     dreaming
    -0.80
     praying
    -0.77
     tweeting
    -0.76
     aware
    -0.76
     inspecting
    -0.75
     imagining
    -0.74
     preparing
    -0.73
     planning
    -0.73
     plotting
    -0.72
    POSITIVE LOGITS
     coincide
    1.27
     occur
    1.19
     intensify
    1.13
     diminish
    1.08
     detract
    1.05
     encompass
    1.04
     happen
    1.03
     trickle
    1.03
     culmin
    1.03
     outweigh
    1.03
    Activations Density 0.291%

    No Known Activations