© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5414
    Prev
    Next
    INDEX
    Explanations

    brand names and product-related terms

    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
    460
    +0.10
    0.5%
    412
    +0.10
    0.5%
    533
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.10
    0.03
    567
    +0.10
    0.02
    343
    +0.10
    0.03
    Negative Logits
    ï¸ı
    -0.79
    IELD
    -0.73
    ivas
    -0.72
    ulhu
    -0.69
    othal
    -0.69
    ostics
    -0.67
    enko
    -0.66
    pora
    -0.65
    Pod
    -0.64
    pel
    -0.64
    POSITIVE LOGITS
    çĭ
    0.69
     Drawn
    0.65
     ABE
    0.63
    EStreamFrame
    0.60
    quickShipAvailable
    0.59
    æ©
    0.58
     precip
    0.58
     {*
    0.57
     Hig
    0.57
    大
    0.56
    Activations Density 0.121%

    No Known Activations