© 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 EvalsExportsAPI 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. 29254
    Prev
    Next
    INDEX
    Explanations

    elements relating to flashbacks or retrospection

    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
    242
    +0.12
    0.6%
    32
    +0.11
    0.5%
    494
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.13
    479
    +0.11
    0.01
    137
    +0.10
    0.00
    Negative Logits
     Ber
    -0.89
    bett
    -0.71
    ricks
    -0.70
     todd
    -0.70
    jam
    -0.69
     gut
    -0.68
     Goff
    -0.68
     cellar
    -0.68
    itt
    -0.67
     Beth
    -0.67
    POSITIVE LOGITS
     X
    2.67
    X
    2.34
     XX
    1.67
     Xen
    1.57
    XM
    1.54
     XI
    1.50
     XXX
    1.50
     XV
    1.50
     Xavier
    1.49
    XX
    1.48
    Activations Density 2.956%

    No Known Activations