© 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. 4645
    Prev
    Next
    INDEX
    Explanations

    references to rights, citizenship, and social responsibilities

    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
    277
    +0.12
    0.6%
    227
    +0.11
    0.5%
    218
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.12
    0.04
    713
    +0.11
    0.02
    144
    +0.11
    0.02
    Negative Logits
     STATS
    -0.76
     Simulator
    -0.71
    COMPLE
    -0.71
     Valid
    -0.70
    UX
    -0.69
     tasting
    -0.69
     spotting
    -0.68
    ople
    -0.67
     prosper
    -0.66
    ilts
    -0.61
    POSITIVE LOGITS
     entitle
    0.86
    edient
    0.83
     attached
    0.77
     accustomed
    0.73
     attach
    0.72
     pend
    0.72
     belonged
    0.72
     subscrib
    0.72
     relates
    0.72
    limits
    0.72
    Activations Density 0.585%

    No Known Activations