© 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. 8-RES_POST_32K-OAI
    11. 8285
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "to"

    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
    314
    +0.21
    1.0%
    145
    +0.13
    0.6%
    242
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.21
    0.07
    718
    +0.13
    0.06
    104
    +0.10
    0.04
    Negative Logits
     impair
    -0.81
     require
    -0.78
     adhere
    -0.78
     simultaneously
    -0.76
     contribut
    -0.76
     impose
    -0.75
     behave
    -0.74
     effectively
    -0.73
     erase
    -0.73
     contradict
    -0.73
    POSITIVE LOGITS
    wered
    0.93
    hill
    0.83
    mber
    0.79
    leaf
    0.79
    gged
    0.77
    cott
    0.77
    ulum
    0.74
    ggles
    0.72
    third
    0.70
    asted
    0.69
    Activations Density 0.364%

    No Known Activations