© 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. 4-RES-JB
    11. 7497
    Prev
    Next
    INDEX
    Explanations

    foreign words or proper nouns containing specific characters 'Äį'

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and locations

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

    No Comments

    Negative Logits
    Ü
    -0.71
    Interstitial
    -0.69
    AMI
    -0.67
    GBT
    -0.67
    pert
    -0.67
     fortun
    -0.66
    essage
    -0.65
     Azerbai
    -0.64
    comb
    -0.63
    istically
    -0.62
    POSITIVE LOGITS
    ijn
    0.96
    keye
    0.83
    rador
    0.79
    artney
    0.79
    sie
    0.77
    rium
    0.77
    hess
    0.76
    yr
    0.74
    keyes
    0.73
    ovo
    0.72
    Activations Density 0.018%

    No Known Activations