© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 27075
    Prev
    Next
    INDEX
    Explanations

    occurrences of the article "a"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    374
    +0.14
    0.6%
    599
    +0.12
    0.5%
    756
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.14
    0.10
    159
    +0.12
    0.07
    328
    +0.10
    0.06
    Negative Logits
    orsi
    -0.81
    iologist
    -0.69
    reon
    -0.67
    ominated
    -0.67
    addafi
    -0.66
     Influence
    -0.66
    retched
    -0.63
    redit
    -0.63
    allion
    -0.62
    annis
    -0.61
    POSITIVE LOGITS
     hurry
    1.50
     manner
    1.47
     nutshell
    1.36
     bid
    1.08
     heartbeat
    1.00
     way
    0.99
     fashion
    0.98
     pinch
    0.96
     guise
    0.93
     timely
    0.91
    Activations Density 0.384%

    No Known Activations