© 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. 5376
    Prev
    Next
    INDEX
    Explanations

    instances of specific scenarios involving people in different locations and situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "when" followed by events

    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
    Score
    -0.75
    ETF
    -0.75
    2020
    -0.73
    yy
    -0.71
    equal
    -0.68
    COMPLE
    -0.65
    kamp
    -0.65
    ãĥĺ
    -0.65
    954
    -0.63
    vote
    -0.63
    POSITIVE LOGITS
     suddenly
    1.17
    uddenly
    0.96
     sudden
    0.90
     tragedy
    0.90
     Suddenly
    0.87
     gunfire
    0.86
     notices
    0.85
     unexpectedly
    0.85
     mysteriously
    0.84
     gunshots
    0.81
    Activations Density 0.224%

    No Known Activations