© 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. 6245
    Prev
    Next
    INDEX
    Explanations

    elements related to dietary measurements and nutritional questions

    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
    208
    +0.09
    0.4%
    731
    +0.09
    0.4%
    750
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.09
    0.18
    640
    +0.09
    0.17
    255
    +0.09
    0.14
    Negative Logits
    ĪĴ
    -0.81
    illance
    -0.74
     facade
    -0.74
     playbook
    -0.72
     hij
    -0.70
     lockdown
    -0.69
     disguise
    -0.69
     malf
    -0.67
     dialogue
    -0.67
    hid
    -0.65
    POSITIVE LOGITS
    Maximum
    1.19
     Calcul
    1.14
    Average
    1.13
     Average
    1.12
     calculated
    1.12
     averages
    1.10
    Percent
    1.09
     averaged
    1.06
     multiplied
    1.06
    average
    1.05
    Activations Density 2.570%

    No Known Activations