© 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. 624
    Prev
    Next
    INDEX
    Explanations

    the word "taken" at various intensities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "taken" and its variations

    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
    eers
    -0.82
    lich
    -0.72
    tions
    -0.67
    tor
    -0.63
    ulo
    -0.60
    cape
    -0.60
    ventures
    -0.59
    tion
    -0.59
    glers
    -0.59
    vine
    -0.59
    POSITIVE LOGITS
     aback
    1.53
    aways
    1.21
     advantage
    0.98
     cogn
    0.92
     care
    0.90
     away
    0.85
     hostage
    0.81
    OVER
    0.81
    away
    0.79
    offs
    0.77
    Activations Density 0.038%

    No Known Activations