© 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. 2301
    Prev
    Next
    INDEX
    Explanations

    the word "garden" with different variations in spelling and contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "warden" and its variations

    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
     Chimera
    -0.68
    ebin
    -0.68
    awaru
    -0.67
    umin
    -0.67
    oric
    -0.62
     Tinker
    -0.62
    ouri
    -0.62
    attering
    -0.62
    NULL
    -0.61
    psc
    -0.60
    POSITIVE LOGITS
    arden
    1.01
    bats
    0.89
    gency
    0.79
     Restaur
    0.78
    alty
    0.76
    burg
    0.75
    mans
    0.71
    felt
    0.70
    è»
    0.70
    stad
    0.70
    Activations Density 0.020%

    No Known Activations