© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 29300
    Prev
    Next
    INDEX
    Explanations

    references to instant messaging (IM) services

    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
    566
    +0.15
    0.7%
    264
    +0.12
    0.5%
    641
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    264
    +0.15
    0.01
    566
    +0.12
    0.01
    314
    +0.11
    -0.00
    Negative Logits
    issan
    -0.85
    ledge
    -0.85
    quez
    -0.84
    ozo
    -0.73
    isting
    -0.72
    ichi
    -0.72
    sei
    -0.71
    ÃŃa
    -0.69
    ional
    -0.69
    nown
    -0.68
    POSITIVE LOGITS
    PLIED
    1.13
    HO
    1.11
    MED
    1.09
    Db
    1.06
    AX
    0.96
    AGE
    0.95
    achine
    0.89
    ORY
    0.88
    MAC
    0.83
    PROV
    0.81
    Activations Density 0.096%

    No Known Activations