© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 10734
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a person named Liu

    oai_token-act-pair · gpt-3.5-turbo

    the name "Liu" and occurrences of specific terms related to health and disease

    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
    gomery
    -0.79
     Ryder
    -0.78
    ting
    -0.73
    yers
    -0.73
    ired
    -0.71
    nes
    -0.70
    tes
    -0.69
    ledge
    -0.69
     Profession
    -0.67
    esley
    -0.67
    POSITIVE LOGITS
     Bei
    1.15
     corrid
    0.81
     Xia
    0.78
     Panda
    0.75
    cci
    0.75
     Liu
    0.75
    ofi
    0.74
    EStreamFrame
    0.71
     Cao
    0.71
    ¥ŀ
    0.70
    Activations Density 0.015%

    No Known Activations