© 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. 30527
    Prev
    Next
    INDEX
    Explanations

    specific initials or acronyms often associated with identities or affiliations

    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
    613
    +0.11
    0.5%
    71
    +0.10
    0.5%
    455
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    530
    +0.11
    0.05
    659
    +0.10
    0.04
    613
    +0.10
    0.03
    Negative Logits
    S
    -1.04
    PB
    -0.98
    PF
    -0.95
    CB
    -0.94
    SI
    -0.92
    TG
    -0.90
    DERR
    -0.89
    Rs
    -0.88
    PK
    -0.88
    SF
    -0.88
    POSITIVE LOGITS
    uria
    0.70
    ename
    0.66
    illac
    0.60
    idates
    0.60
    aria
    0.59
    ulates
    0.59
     dictatorship
    0.58
    strings
    0.58
    arius
    0.58
    arians
    0.58
    Activations Density 0.417%

    No Known Activations