© 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. 5413
    Prev
    Next
    INDEX
    Explanations

    topics related to substance use and associated cultural or societal issues

    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
    252
    +0.14
    0.6%
    373
    +0.13
    0.6%
    468
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.19
    592
    +0.13
    0.09
    67
    +0.11
    0.11
    Negative Logits
     Rasmussen
    -0.67
     UNC
    -0.67
     Oro
    -0.65
     Camb
    -0.64
     Xen
    -0.64
     Double
    -0.64
     Kul
    -0.64
     Uri
    -0.63
     Plymouth
    -0.63
     Yel
    -0.62
    POSITIVE LOGITS
     itself
    0.97
    ophobia
    0.77
    entimes
    0.76
    iculture
    0.73
     oneself
    0.73
    ipedia
    0.73
     causation
    0.73
     versus
    0.70
    cigarettes
    0.69
     intrinsically
    0.69
    Activations Density 2.135%

    No Known Activations