© 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. 6094
    Prev
    Next
    INDEX
    Explanations

    references to academic studies and topics related to minimum wage and its effects

    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
    393
    +0.12
    0.5%
    84
    +0.10
    0.5%
    361
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.08
    97
    +0.10
    0.04
    385
    +0.10
    0.07
    Negative Logits
    bender
    -0.80
    WHERE
    -0.76
    âĨij
    -0.71
    Secondly
    -0.70
    whatever
    -0.70
    starter
    -0.70
     wherever
    -0.68
     sooner
    -0.68
    entimes
    -0.67
     istg
    -0.67
    POSITIVE LOGITS
     Contemporary
    1.03
     Selected
    0.91
     Everyday
    0.83
     Newly
    0.81
     Highly
    0.81
     Mathemat
    0.80
     Aging
    0.78
     Forensic
    0.78
     Emerging
    0.76
     Experimental
    0.76
    Activations Density 0.613%

    No Known Activations