© 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. 1-RES-JB
    11. 14352
    Prev
    Next
    INDEX
    Explanations

    phrases ending with 'lia'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Lia" and variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lighting
    -0.89
    iaries
    -0.80
    ENDED
    -0.75
    hai
    -0.73
    ipation
    -0.71
    nian
    -0.70
    lit
    -0.70
    ANK
    -0.69
    etheless
    -0.69
    ulation
    -0.69
    POSITIVE LOGITS
    zzo
    1.17
     Amend
    1.02
    xus
    0.95
    ppo
    0.91
    emis
    0.89
    zzi
    0.88
    lia
    0.86
    lla
    0.86
    ffect
    0.83
    zza
    0.81
    Activations Density 0.018%

    No Known Activations