© 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. 5923
    Prev
    Next
    INDEX
    Explanations

    references to rights and their holders in a legal or societal context

    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
    357
    +0.11
    0.5%
    224
    +0.11
    0.5%
    559
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.11
    0.03
    575
    +0.11
    0.03
    132
    +0.10
    0.03
    Negative Logits
     Solitaire
    -0.78
     Remastered
    -0.67
     Claus
    -0.66
    ools
    -0.65
     Daylight
    -0.65
     Suggest
    -0.64
    BALL
    -0.63
    aco
    -0.63
     Sark
    -0.59
     Sins
    -0.58
    POSITIVE LOGITS
     holders
    0.90
    rights
    0.87
     rights
    0.86
     conferred
    0.86
    holders
    0.84
    holder
    0.82
     Rights
    0.81
    fulness
    0.79
     protections
    0.79
    lessness
    0.78
    Activations Density 0.051%

    No Known Activations