© 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. 28388
    Prev
    Next
    INDEX
    Explanations

    terms related to immune response regulation and endocrine signaling

    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
    455
    +0.16
    0.7%
    362
    +0.13
    0.6%
    239
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    455
    +0.16
    0.15
    67
    +0.13
    0.11
    362
    +0.10
    0.12
    Negative Logits
    ãĤ£
    -0.88
    someone
    -0.88
    Something
    -0.86
    ãĥĥ
    -0.85
    prints
    -0.83
    Tokens
    -0.81
    leans
    -0.80
    Think
    -0.80
    puters
    -0.80
    isSpecialOrderable
    -0.80
    POSITIVE LOGITS
     susceptibility
    1.03
     heterogeneity
    0.99
     oxidative
    0.96
     endogenous
    0.94
     characterization
    0.93
     apopt
    0.93
     pharmac
    0.92
     recruitment
    0.91
     acute
    0.90
     intra
    0.89
    Activations Density 1.044%

    No Known Activations