© 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. 27862
    Prev
    Next
    INDEX
    Explanations

    instances of the concept of disappearance

    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
    348
    +0.11
    0.5%
    373
    +0.10
    0.5%
    410
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    759
    +0.11
    0.02
    351
    +0.10
    0.02
    271
    +0.10
    0.02
    Negative Logits
    76561
    -0.76
     Tennis
    -0.72
    eering
    -0.70
    ullah
    -0.68
    itcher
    -0.61
    umes
    -0.59
     inferred
    -0.58
    alist
    -0.57
    ios
    -0.57
    erity
    -0.57
    POSITIVE LOGITS
     mysteriously
    0.97
     altogether
    0.93
     into
    0.91
     forever
    0.81
     entirely
    0.81
     completely
    0.81
    owship
    0.80
     INTO
    0.78
     peacefully
    0.77
     overboard
    0.75
    Activations Density 0.054%

    No Known Activations