© 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. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 23864
    Prev
    Next
    INDEX
    Explanations

    special characters or punctuation in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_mlp_out
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.29
    1.7%
    63
    +0.14
    0.8%
    271
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.29
    0.06
    458
    +0.14
    0.04
    231
    +0.14
    0.05
    Negative Logits
    rapy
    -1.65
    plit
    -1.50
    porary
    -1.43
    emic
    -1.38
    lu
    -1.32
    --------------------------------------------------------------------------------
    -1.29
    FPar
    -1.29
    ftp
    -1.25
     outpatient
    -1.24
     PAC
    -1.22
    POSITIVE LOGITS
    ĻĤ
    3.19
    Ń
    3.16
    ŀ
    2.93
    ĸ´
    2.81
    ·¸
    2.70
    Īĺ
    2.66
    »¿
    2.66
    ¯
    2.62
    ĩ
    2.60
    ļ
    2.60
    Activations Density 0.436%

    No Known Activations