© 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. 15166
    Prev
    Next
    INDEX
    Explanations

    words related to historical periods or settings, specifically focusing on the Victorian era

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the Victorian era and its cultural aspects

    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
    earance
    -0.91
    words
    -0.87
    spring
    -0.82
    iotic
    -0.81
    */(
    -0.80
    cific
    -0.80
    rencies
    -0.75
    swer
    -0.74
    iotics
    -0.74
    chery
    -0.73
    POSITIVE LOGITS
     Era
    0.83
     Victorian
    0.80
     Gentleman
    0.77
     Gothic
    0.77
     Railway
    0.76
     sensibilities
    0.71
     Century
    0.68
     incarnation
    0.67
     Fantasy
    0.66
     fantas
    0.66
    Activations Density 0.008%

    No Known Activations