© 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. 27345
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers or data references

    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
    40
    +0.14
    0.6%
    633
    +0.12
    0.5%
    641
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.14
    0.06
    442
    +0.12
    0.06
    153
    +0.11
    0.04
    Negative Logits
    BN
    -0.79
    é¾
    -0.78
    ylene
    -0.77
    omatic
    -0.75
    373
    -0.72
    ril
    -0.72
     mammal
    -0.71
     Bog
    -0.71
    pi
    -0.70
     Mub
    -0.69
    POSITIVE LOGITS
     14
    1.47
    14
    1.42
     15
    1.35
    15
    1.33
    150
    1.22
    149
    1.18
    1500
    1.17
    148
    1.14
    152
    1.13
     150
    1.11
    Activations Density 1.668%

    No Known Activations