© 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. 0-RES-JB
    11. 5323
    Prev
    Next
    INDEX
    Explanations

    names or terms with the suffix '-gaard'

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly surnames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Taj
    -0.75
     Poc
    -0.74
     Spit
    -0.71
     Sunshine
    -0.67
     Fancy
    -0.66
     Torch
    -0.63
     unaccount
    -0.62
     tram
    -0.62
     Uzbek
    -0.61
     capitals
    -0.60
    POSITIVE LOGITS
    gaard
    4.30
    gard
    3.73
    gart
    1.84
    gren
    1.63
    meyer
    1.33
    bard
    1.26
    holm
    1.19
    gra
    1.16
    hower
    1.15
    agar
    1.14
    Activations Density 0.036%

    No Known Activations