© 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. 31722
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating possibility, obligation, or necessity

    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
    373
    +0.11
    0.5%
    390
    +0.10
    0.5%
    361
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.11
    0.16
    49
    +0.10
    0.13
    139
    +0.10
    0.13
    Negative Logits
    />
    -0.57
     IPM
    -0.55
    ibaba
    -0.55
     Spectre
    -0.53
     Americ
    -0.53
     unbeliev
    -0.53
     Georgian
    -0.51
     violet
    -0.50
     defaults
    -0.50
     warr
    -0.49
    POSITIVE LOGITS
    've
    1.51
    have
    1.35
     have
    1.26
     HAVE
    1.10
     Have
    1.09
    Have
    1.06
    has
    1.03
    had
    0.94
    Had
    0.93
     has
    0.90
    Activations Density 0.853%

    No Known Activations