© 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. 10-RES-JB
    11. 13833
    Prev
    Next
    INDEX
    Explanations

    phrases related to validation or verification

    oai_token-act-pair · gpt-3.5-turbo

    terms related to validity or legitimacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.79
    hedon
    -0.73
     preferring
    -0.66
     traged
    -0.65
    mania
    -0.62
    hell
    -0.62
     superflu
    -0.62
     Alive
    -0.62
    hedral
    -0.61
    Mania
    -0.60
    POSITIVE LOGITS
    ating
    1.52
    ators
    1.41
    ator
    1.33
    ates
    1.21
    ated
    1.15
    ations
    1.09
    atable
    1.05
    ATING
    1.04
    ation
    0.97
    iated
    0.92
    Activations Density 0.026%

    No Known Activations