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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 29516
    Prev
    Next
    INDEX
    Explanations

    the word "stay" and its variations, indicating a focus on persistence or continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    55
    +0.10
    0.5%
    195
    +0.10
    0.5%
    531
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.10
    0.03
    646
    +0.10
    0.03
    152
    +0.10
    0.03
    Negative Logits
     Parables
    -0.72
    DragonMagazine
    -0.70
    HCR
    -0.69
    rely
    -0.68
    naire
    -0.67
     Proceed
    -0.65
    eus
    -0.64
    heid
    -0.64
    MRI
    -0.63
     Mayhem
    -0.63
    POSITIVE LOGITS
     afloat
    1.14
    cation
    1.04
     alive
    1.02
     tuned
    1.00
     awake
    0.96
     classy
    0.86
     intact
    0.84
     awhile
    0.81
     away
    0.79
     put
    0.78
    Activations Density 0.069%

    No Known Activations