© 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. 22817
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating location or motion

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to physical actions and movements

    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
    ographically
    -0.88
    speak
    -0.87
    iably
    -0.87
    Ó
    -0.87
    ometimes
    -0.86
    paio
    -0.86
    icz
    -0.84
    entimes
    -0.84
    albeit
    -0.84
    aciously
    -0.83
    POSITIVE LOGITS
     original
    0.95
     latest
    0.86
     conclusion
    0.85
     assumption
    0.85
     aftermath
    0.84
     destination
    0.81
     exception
    0.81
     WS
    0.81
     vicinity
    0.80
     probe
    0.80
    Activations Density 0.563%

    No Known Activations