© 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. 7103
    Prev
    Next
    INDEX
    Explanations

    phrases related to reporting, journalism, or media citations

    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
    113
    +0.12
    0.5%
    314
    +0.11
    0.5%
    373
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    113
    +0.12
    0.08
    373
    +0.11
    -0.08
    314
    +0.11
    -0.02
    Negative Logits
     pav
    -0.71
    aceae
    -0.71
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.67
    ware
    -0.65
     stockp
    -0.63
     refunds
    -0.63
     Malfoy
    -0.61
    inventory
    -0.61
     leveling
    -0.60
     reintrodu
    -0.59
    POSITIVE LOGITS
     Daily
    1.19
    News
    1.17
    Daily
    1.11
     Telegraph
    1.11
     News
    1.10
    aretz
    1.08
    Journal
    1.07
     Herald
    1.07
     Tribune
    1.06
     Reporter
    1.06
    Activations Density 3.520%

    No Known Activations