© 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. 6354
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific entities being known for certain characteristics or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a specific attribute or feature associated with various subjects

    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
    Reviewed
    -0.81
    soever
    -0.75
    OTAL
    -0.75
    MRI
    -0.71
    York
    -0.70
    CNN
    -0.69
    Registered
    -0.66
    down
    -0.65
    Compare
    -0.65
    Correction
    -0.64
    POSITIVE LOGITS
    geries
    0.92
     having
    0.86
     cracking
    0.85
     producing
    0.84
     creating
    0.78
     delivering
    0.77
     being
    0.77
     exporting
    0.76
     discriminating
    0.76
     storing
    0.76
    Activations Density 0.088%

    No Known Activations