© 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. 10-RES_POST_32K-OAI
    11. 31013
    Prev
    Next
    INDEX
    Explanations

    mentions of specific languages or language attributes

    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
    297
    +0.15
    0.7%
    694
    +0.12
    0.6%
    280
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    166
    +0.15
    0.14
    280
    +0.12
    0.12
    426
    +0.11
    0.08
    Negative Logits
    MS
    -1.10
     Maz
    -1.07
    MT
    -1.06
    MAT
    -1.04
    ME
    -1.01
    mt
    -1.01
     Mol
    -1.01
     Mend
    -1.00
    MET
    -1.00
     MEM
    -1.00
    POSITIVE LOGITS
    wr
    0.98
    owsky
    0.96
    ucket
    0.93
    hower
    0.92
    arrow
    0.88
    oult
    0.88
    ucking
    0.86
    UCK
    0.86
    row
    0.85
    crow
    0.85
    Activations Density 6.444%

    No Known Activations