© 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. 28638
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "to" and related prepositions in various contexts

    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
    648
    +0.11
    0.5%
    682
    +0.11
    0.5%
    182
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.11
    0.08
    90
    +0.11
    0.07
    616
    +0.09
    0.06
    Negative Logits
    ãĥ³ãĤ¸
    -1.04
    ãĥ¼ãĤ¯
    -0.79
    recated
    -0.79
    leep
    -0.78
    rift
    -0.75
    pictured
    -0.75
    anoia
    -0.73
    phans
    -0.72
    å¦
    -0.72
    anooga
    -0.71
    POSITIVE LOGITS
     arrival
    1.43
     completion
    1.39
     receipt
    1.36
     publication
    1.33
     commencement
    1.33
     issuance
    1.32
     entering
    1.27
     enactment
    1.26
     entry
    1.25
     signing
    1.24
    Activations Density 0.620%

    No Known Activations