© 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. 9971
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to significant moments or events within a specific context

    oai_token-act-pair · gpt-3.5-turbo

    references to significant topics or themes in discussions

    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
    quit
    -0.84
    nces
    -0.80
    leted
    -0.75
    LEASE
    -0.72
    efer
    -0.71
    chu
    -0.71
    =#
    -0.71
    isson
    -0.71
    ngth
    -0.70
    utterstock
    -0.70
    POSITIVE LOGITS
     midst
    1.38
     wake
    1.18
     aftermath
    1.12
     meantime
    1.08
     direction
    1.04
     vicinity
    0.99
     workings
    0.98
     relationship
    0.97
     pursuit
    0.93
     psyche
    0.93
    Activations Density 0.226%

    No Known Activations