© 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 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. 28424
    Prev
    Next
    INDEX
    Explanations

    verbs and modal verbs indicating possibility or obligation

    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
    314
    +0.16
    0.7%
    580
    +0.12
    0.5%
    499
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.16
    0.14
    139
    +0.12
    0.12
    49
    +0.11
    0.11
    Negative Logits
     Nort
    -0.65
     welf
    -0.64
     Roose
    -0.59
     advoc
    -0.59
     Instrument
    -0.58
     Flex
    -0.57
     domest
    -0.57
     Manifest
    -0.57
     Anon
    -0.56
     Gron
    -0.56
    POSITIVE LOGITS
    etheless
    0.87
     attest
    0.84
     nevertheless
    0.80
     suddenly
    0.78
     nonetheless
    0.76
     likewise
    0.72
    ãĤ¤ãĥĪ
    0.72
     thereby
    0.72
    ially
    0.71
    ifles
    0.68
    Activations Density 2.160%

    No Known Activations