© 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. 28127
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to immune response and inflammation

    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
    373
    +0.10
    0.5%
    399
    +0.10
    0.4%
    516
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.10
    0.11
    516
    +0.10
    0.10
    239
    +0.10
    0.08
    Negative Logits
    DCS
    -0.79
    uana
    -0.75
    raints
    -0.75
     placebo
    -0.73
    itored
    -0.70
     DSM
    -0.69
     indic
    -0.68
     Cosponsors
    -0.68
     informant
    -0.66
    soDeliveryDate
    -0.66
    POSITIVE LOGITS
     accumulation
    0.94
     degener
    0.92
     nec
    0.90
     apopt
    0.85
     infiltrate
    0.85
     stagnation
    0.83
     buildup
    0.83
     oxidative
    0.82
     destruction
    0.82
     atro
    0.82
    Activations Density 1.591%

    No Known Activations