© 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. 26901
    Prev
    Next
    INDEX
    Explanations

    conditional and future tense verbs indicating obligations or expectations

    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
    551
    +0.12
    0.5%
    756
    +0.11
    0.5%
    602
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.12
    0.19
    139
    +0.11
    0.16
    49
    +0.11
    0.13
    Negative Logits
    Its
    -1.18
     Its
    -1.06
     its
    -0.93
     itself
    -0.91
     ITS
    -0.86
    its
    -0.67
    issance
    -0.65
    Ö
    -0.63
    alion
    -0.63
    sole
    -0.62
    POSITIVE LOGITS
     themselves
    1.38
     prolifer
    1.15
     respectively
    0.93
    selves
    0.92
     respective
    0.86
     collectively
    0.86
     selves
    0.86
     individually
    0.83
     clustered
    0.83
     their
    0.81
    Activations Density 0.966%

    No Known Activations