© 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. 4155
    Prev
    Next
    INDEX
    Explanations

    the substring "za" within words

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Za" or similar variations, likely focusing on a specific individual or character

    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
    lessly
    -0.97
    amental
    -0.76
    ramer
    -0.73
     glim
    -0.69
    ician
    -0.69
    ritional
    -0.69
    bread
    -0.68
    aceous
    -0.67
    LESS
    -0.66
     satell
    -0.66
    POSITIVE LOGITS
    emon
    0.85
    quez
    0.85
     Motorsport
    0.84
    ombie
    0.83
    zza
    0.81
    ombies
    0.81
    eta
    0.79
    ppa
    0.78
    zz
    0.77
    illes
    0.77
    Activations Density 0.012%

    No Known Activations