© 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. 31336
    Prev
    Next
    INDEX
    Explanations

    symbols and operators related to logical and statistical comparisons

    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
    735
    +0.11
    0.5%
    9
    +0.10
    0.5%
    673
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    747
    +0.11
    0.03
    631
    +0.10
    0.02
    61
    +0.09
    0.03
    Negative Logits
    odan
    -0.98
    tis
    -0.91
    SPA
    -0.82
    ANA
    -0.81
    fur
    -0.79
    atari
    -0.76
    DragonMagazine
    -0.75
    channelAvailability
    -0.74
    ItemImage
    -0.72
    wl
    -0.72
    POSITIVE LOGITS
     statistical
    0.78
     0
    0.72
     estimate
    0.67
     statistically
    0.67
     .
    0.67
     ..............
    0.65
     (.
    0.60
     1900
    0.58
     2000
    0.58
     detection
    0.58
    Activations Density 0.245%

    No Known Activations