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

    Neuronpedia

    Jacobian LensNEW
    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. 4515
    Prev
    Next
    INDEX
    Explanations

    mentions of "media" in various contexts

    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
    65
    +0.10
    0.5%
    140
    +0.10
    0.5%
    464
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    132
    +0.10
    0.03
    336
    +0.10
    0.03
    662
    +0.10
    0.03
    Negative Logits
    abad
    -0.67
     satirical
    -0.66
    partisan
    -0.64
    sung
    -0.62
     crooked
    -0.60
     Rasmussen
    -0.60
     sting
    -0.59
    0000000
    -0.58
     phony
    -0.58
    anks
    -0.57
    POSITIVE LOGITS
    eval
    1.07
    wiki
    0.94
    artney
    0.80
    fire
    0.77
     Compos
    0.76
     MPEG
    0.72
    Fire
    0.71
    player
    0.70
    enc
    0.70
    hare
    0.68
    Activations Density 0.101%

    No Known Activations