© 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. 8-RES_POST_32K-OAI
    11. 8662
    Prev
    Next
    INDEX
    Explanations

    references to personal pronouns indicating request or desire for action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    279
    +0.11
    0.5%
    601
    +0.11
    0.5%
    512
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    279
    +0.11
    0.05
    105
    +0.11
    0.04
    515
    +0.10
    0.04
    Negative Logits
    raid
    -0.72
    idding
    -0.71
    bia
    -0.71
    uum
    -0.70
    post
    -0.70
    aters
    -0.70
    edi
    -0.68
     relates
    -0.65
    sum
    -0.64
    worthy
    -0.64
    POSITIVE LOGITS
     recourse
    0.92
     guidance
    0.86
     access
    0.85
     ample
    0.85
     pointers
    0.81
     glimps
    0.80
     insight
    0.79
     unlimited
    0.78
     advice
    0.77
     insights
    0.76
    Activations Density 0.149%

    No Known Activations