© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 24503
    Prev
    Next
    INDEX
    Explanations

    Japanese characters and names

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to complex symbolic or semantic representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     specificity
    -0.79
    enegger
    -0.79
    eanor
    -0.75
     Consent
    -0.75
    buquerque
    -0.72
    anooga
    -0.72
    ebus
    -0.72
     Hannity
    -0.70
     advertisers
    -0.70
    olphins
    -0.69
    POSITIVE LOGITS
    Ĺ
    1.10
    ¨
    1.06
    士
    1.05
    ħ
    1.04
    °
    1.02
    Ļ
    0.97
    Ł
    0.97
    ļ
    0.96
    åº
    0.96
    çİĭ
    0.95
    Activations Density 0.207%

    No Known Activations