© 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. 16145
    Prev
    Next
    INDEX
    Explanations

    phrases indicating suitability or compatibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe suitability or perfect matches for various contexts or items

    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
    ceivable
    -0.77
    again
    -0.75
    RIP
    -0.74
    named
    -0.73
    uthor
    -0.72
    izzle
    -0.69
    soever
    -0.69
    ))))
    -0.69
    buster
    -0.68
    osal
    -0.67
    POSITIVE LOGITS
     beginners
    1.25
     storing
    1.10
     transporting
    0.97
     detecting
    0.97
     navigating
    0.95
     dealing
    0.92
     maximizing
    0.92
     emergencies
    0.91
     framing
    0.91
     combating
    0.91
    Activations Density 0.134%

    No Known Activations