© 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. 28614
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions or dependencies

    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
    71
    +0.15
    0.7%
    514
    +0.11
    0.5%
    459
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.15
    0.10
    669
    +0.11
    0.07
    362
    +0.11
    0.07
    Negative Logits
    otomy
    -0.81
    ãĥĺ
    -0.81
    cffffcc
    -0.72
    ãĥĪ
    -0.70
    ynes
    -0.66
    lime
    -0.66
    seys
    -0.66
    luaj
    -0.65
    trop
    -0.65
    fff
    -0.64
    POSITIVE LOGITS
     factors
    0.96
     anticipated
    0.94
     previous
    0.89
     prevailing
    0.89
     circumstances
    0.87
     whether
    0.85
     receipt
    0.82
     changes
    0.81
     availability
    0.81
     subsequent
    0.80
    Activations Density 0.590%

    No Known Activations