© 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. 8-RES_POST_32K-OAI
    11. 5985
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs indicating existence or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    59
    +0.11
    0.5%
    757
    +0.10
    0.5%
    317
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.11
    0.03
    59
    +0.10
    0.03
    449
    +0.10
    0.03
    Negative Logits
    ragon
    -0.65
    ares
    -0.62
    chairs
    -0.60
    arez
    -0.60
    pod
    -0.59
    lass
    -0.59
    regate
    -0.58
    CLOSE
    -0.57
     sacrific
    -0.55
    dayName
    -0.55
    POSITIVE LOGITS
     there
    1.06
     it
    0.91
     they
    0.88
    there
    0.85
    tis
    0.79
     he
    0.72
    éŃĶ
    0.72
     we
    0.71
     she
    0.67
    berra
    0.67
    Activations Density 0.122%

    No Known Activations