© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 10637
    Prev
    Next
    INDEX
    Explanations

    words related to rituals, ceremonies, or formal events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ceremonial and solemn occasions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artment
    -0.80
    izoph
    -0.78
    Solution
    -0.78
     Hust
    -0.73
    ãĥ´
    -0.71
    Iterator
    -0.71
    Weak
    -0.69
    Kids
    -0.69
    pson
    -0.68
    orno
    -0.67
    POSITIVE LOGITS
     ceremonial
    1.17
     ceremonies
    0.96
     ausp
    0.96
     ceremony
    0.95
     ceremon
    0.93
     celebr
    0.92
     procession
    0.88
     pomp
    0.88
     Cere
    0.86
     festivities
    0.86
    Activations Density 0.022%

    No Known Activations