© 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. 10-RES_POST_32K-OAI
    11. 29375
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Her" in various forms

    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
    +0.17
    0.7%
    218
    +0.11
    0.5%
    683
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    15
    +0.17
    0.03
    694
    +0.11
    0.01
    167
    +0.10
    0.01
    Negative Logits
    BuyableInstoreAndOnline
    -0.62
     untreated
    -0.62
     uncond
    -0.61
     construed
    -0.60
     lett
    -0.60
     unequivocally
    -0.59
     stricken
    -0.59
     Jiu
    -0.59
     urgently
    -0.59
     scares
    -0.59
    POSITIVE LOGITS
    itage
    1.36
    mit
    1.27
    cule
    1.26
    acles
    1.23
    oes
    1.21
    bal
    1.18
    pes
    1.17
    rick
    1.12
    aeus
    1.12
    bie
    1.10
    Activations Density 0.133%

    No Known Activations