© 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. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5005
    Prev
    Next
    INDEX
    Explanations

    references to royalty or royal institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    373
    +0.12
    0.6%
    139
    +0.12
    0.5%
    472
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    290
    +0.12
    0.02
    472
    +0.12
    0.01
    168
    +0.12
    0.02
    Negative Logits
    alach
    -0.72
     Gutenberg
    -0.68
    orer
    -0.66
    arers
    -0.66
    omsky
    -0.66
    icago
    -0.66
    ONES
    -0.65
    arer
    -0.63
    REM
    -0.62
    ARB
    -0.61
    POSITIVE LOGITS
    ty
    1.03
     Caribbean
    0.74
     Arabia
    0.73
     jelly
    0.72
    fac
    0.72
     Chall
    0.69
    ized
    0.69
     Palace
    0.68
    ton
    0.68
     Warrant
    0.68
    Activations Density 0.041%

    No Known Activations