© 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. 31596
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "bas" and related variations as well as high-frequency terms

    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
    152
    +0.10
    0.5%
    92
    +0.10
    0.4%
    118
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.10
    -0.01
    659
    +0.10
    0.04
    232
    +0.09
    0.05
    Negative Logits
    GBT
    -0.71
    orted
    -0.69
    aro
    -0.61
    etsy
    -0.61
    atche
    -0.60
    ort
    -0.58
    ubs
    -0.57
    OUP
    -0.55
     penal
    -0.55
     preventive
    -0.55
    POSITIVE LOGITS
    antine
    0.80
    ins
    0.78
    ine
    0.71
    Alias
    0.67
    mat
    0.62
    zanne
    0.62
    enment
    0.61
    fighters
    0.61
    illing
    0.60
    stadt
    0.59
    Activations Density 0.637%

    No Known Activations