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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 2-RES-JB
    6. 70
    Prev
    Next
    INDEX
    Explanations

    numerals that refer to specific centuries

    oai_token-act-pair · gpt-3.5-turbo

    references to specific centuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words indicating centuries, specifically those suffixed with 'teenth' or 'teenth century'

    oai_token-act-pair · gpt-4-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.78
    ãģĤ
    -0.70
    Tile
    -0.69
    ULE
    -0.68
    RIP
    -0.68
    PE
    -0.67
    RAM
    -0.66
    iguous
    -0.65
    HEAD
    -0.65
    agate
    -0.65
    POSITIVE LOGITS
    eenth
    1.13
     century
    1.05
    teenth
    0.98
    eteenth
    0.96
    ieth
    0.93
     Century
    0.85
    century
    0.84
    irty
    0.84
     nineteenth
    0.83
     eighteenth
    0.83
    Activations Density 0.010%

    No Known Activations