Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8605
    Prev
    Next
    INDEX
    Explanations

    terms related to historical preservation or important cultural significance

    oai_token-act-pair · gpt-3.5-turbo

    references to cultural and historical heritage

    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
    vae
    -0.91
    kers
    -0.79
    ched
    -0.72
    vern
    -0.71
    arters
    -0.68
    hap
    -0.68
    bern
    -0.67
    plet
    -0.67
    pher
    -0.67
    arter
    -0.66
    POSITIVE LOGITS
     heritage
    1.18
    conservancy
    1.01
    artifacts
    0.90
     preservation
    0.87
     arte
    0.81
     relics
    0.78
     museum
    0.74
     legacy
    0.74
    stones
    0.74
    iqueness
    0.74
    Activations Density 0.014%

    No Known Activations