© 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. 28698
    Prev
    Next
    INDEX
    Explanations

    phrases related to immune responses and immunological activities

    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
    314
    +0.11
    0.5%
    724
    +0.10
    0.5%
    56
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    250
    +0.11
    0.13
    36
    +0.10
    0.11
    328
    +0.10
    0.08
    Negative Logits
     damn
    -0.84
     goddamn
    -0.83
     lousy
    -0.82
     Thing
    -0.79
     paycheck
    -0.79
     damned
    -0.79
     ugly
    -0.77
     awfully
    -0.77
     kid
    -0.77
     godd
    -0.76
    POSITIVE LOGITS
    ort
    1.04
    otype
    1.02
    que
    0.97
    prot
    0.85
    terior
    0.85
    Es
    0.84
    lde
    0.84
    otypes
    0.84
    zo
    0.84
    phi
    0.83
    Activations Density 0.490%

    No Known Activations