© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6873
    Prev
    Next
    INDEX
    Explanations

    variations of the word "as" in different contexts

    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
    374
    +0.12
    0.5%
    688
    +0.09
    0.4%
    9
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    767
    +0.12
    0.03
    232
    +0.09
    0.03
    284
    +0.09
    0.03
    Negative Logits
     sleeper
    -0.80
     bott
    -0.66
    ãĤ´
    -0.58
    itta
    -0.57
    KB
    -0.56
     Manit
    -0.55
     bra
    -0.55
     lith
    -0.55
    ashtra
    -0.54
     kb
    -0.54
    POSITIVE LOGITS
    urable
    1.38
    uries
    1.04
    ures
    1.01
    URES
    0.98
    ured
    0.98
    eled
    0.89
    entially
    0.89
    uring
    0.88
    antine
    0.86
    enges
    0.85
    Activations Density 0.236%

    No Known Activations