© 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. 30296
    Prev
    Next
    INDEX
    Explanations

    phrases related to rankings and comparisons in various contexts

    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
    140
    +0.10
    0.5%
    500
    +0.10
    0.5%
    35
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.10
    0.20
    608
    +0.10
    0.17
    566
    +0.10
    0.11
    Negative Logits
     UID
    -0.69
     BEFORE
    -0.64
    UID
    -0.63
    !:
    -0.62
    UGC
    -0.60
    :(
    -0.59
     Firstly
    -0.59
    DNA
    -0.59
     FANT
    -0.58
    Today
    -0.58
    POSITIVE LOGITS
     likewise
    1.09
     theirs
    1.00
     hers
    0.90
     respectively
    0.80
     versa
    0.78
     similarly
    0.77
     TBA
    0.72
     equally
    0.69
     thereafter
    0.68
     thereto
    0.63
    Activations Density 5.623%

    No Known Activations