© 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. 28811
    Prev
    Next
    INDEX
    Explanations

    terms related to changes in economic or social metrics, particularly increasing or decreasing trends

    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
    759
    +0.12
    0.6%
    368
    +0.11
    0.5%
    592
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.12
    0.08
    125
    +0.11
    0.07
    761
    +0.10
    0.07
    Negative Logits
    agher
    -0.78
    ools
    -0.74
    BuyableInstoreAndOnline
    -0.74
    archives
    -0.63
    worms
    -0.63
    oops
    -0.61
     Redemption
    -0.61
    RN
    -0.60
    thing
    -0.58
     Neph
    -0.58
    POSITIVE LOGITS
     markedly
    1.18
     dramatically
    1.15
     sharply
    1.10
     substantially
    1.07
     drastically
    1.01
     significantly
    0.99
     exponentially
    0.96
     noticeably
    0.93
     greatly
    0.92
     accordingly
    0.92
    Activations Density 0.419%

    No Known Activations