© 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. 6-RES-JB
    11. 13488
    Prev
    Next
    INDEX
    Explanations

    phrases related to general statements or overall concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate general statements or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fax
    -0.79
    Future
    -0.77
    letes
    -0.77
    leted
    -0.75
    lyn
    -0.73
    lete
    -0.67
    XL
    -0.66
    Mount
    -0.65
    mented
    -0.64
    Reb
    -0.64
    POSITIVE LOGITS
     relativity
    1.16
    izations
    0.91
     vicinity
    0.86
    ignment
    0.81
     anesthesia
    0.79
    ization
    0.75
     aviation
    0.75
    edia
    0.74
    arily
    0.71
    isations
    0.69
    Activations Density 0.015%

    No Known Activations