© 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. 29966
    Prev
    Next
    INDEX
    Explanations

    references to the word "Dom" or variations thereof, often in relation to dominance or control

    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
    288
    +0.14
    0.6%
    493
    +0.11
    0.5%
    373
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.02
    232
    +0.11
    0.02
    284
    +0.10
    0.01
    Negative Logits
    packing
    -0.77
    SEE
    -0.62
     Bulg
    -0.61
     baths
    -0.59
     arrows
    -0.58
    UGH
    -0.58
     arrow
    -0.58
    Madison
    -0.57
    HCR
    -0.55
    KEN
    -0.55
    POSITIVE LOGITS
    estic
    1.48
    inant
    1.37
    ains
    1.36
    ino
    1.29
    ination
    1.28
    inating
    1.28
    aine
    1.12
    inate
    1.11
    inion
    1.10
    inance
    1.08
    Activations Density 0.079%

    No Known Activations