© 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 EvalsExportsinterp-engineNEWAPI 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. 31383
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns and phrases indicating self-reference

    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
    537
    +0.13
    0.6%
    761
    +0.11
    0.5%
    386
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    761
    +0.13
    0.06
    665
    +0.11
    0.06
    759
    +0.11
    0.05
    Negative Logits
     nightmares
    -0.81
     paralysis
    -0.68
     insomnia
    -0.62
     overdose
    -0.60
     dashed
    -0.59
    PASS
    -0.59
     overdoses
    -0.59
     aggregation
    -0.59
     butterflies
    -0.58
    uminati
    -0.57
    POSITIVE LOGITS
     territ
    0.90
     diplom
    0.89
     firmly
    0.83
    polit
    0.82
     politically
    0.82
     forcefully
    0.80
     ideologically
    0.78
     adequately
    0.77
     fully
    0.74
     properly
    0.74
    Activations Density 0.434%

    No Known Activations