© 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. 26668
    Prev
    Next
    INDEX
    Explanations

    items related to online articles or links

    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
    497
    +0.18
    0.9%
    373
    +0.14
    0.7%
    91
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.18
    -0.01
    374
    +0.14
    -0.01
    659
    +0.12
    0.03
    Negative Logits
    oÄŁ
    -0.69
    SPONSORED
    -0.69
    VERTISEMENT
    -0.68
    GROUND
    -0.68
     behav
    -0.63
     Cipher
    -0.60
    izoph
    -0.60
     precon
    -0.58
    archment
    -0.58
    founded
    -0.58
    POSITIVE LOGITS
     wrench
    0.63
    383
    0.60
    ĸļ
    0.59
     earthqu
    0.58
     332
    0.57
     limb
    0.56
    shaw
    0.56
     Eight
    0.56
     Swe
    0.55
     Shank
    0.54
    Activations Density 0.432%

    No Known Activations