© 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. 0-MLP-SM
    11. 26287
    Prev
    Next
    INDEX
    Explanations

    mentions of configuration settings and parameters in a document

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    +0.21
    1.2%
    376
    +0.14
    0.8%
    250
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    33
    +0.21
    0.01
    221
    +0.14
    0.01
    250
    +0.11
    0.01
    Negative Logits
    ))$,
    -1.64
    ktiv
    -1.61
    ktion
    -1.60
    ))$
    -1.48
    ))$.
    -1.48
    mpi
    -1.46
     slightest
    -1.45
    lla
    -1.44
    ÑĤÑĮ
    -1.42
    vere
    -1.42
    POSITIVE LOGITS
    £
    2.39
    ģ
    2.38
    urable
    2.35
    Ń
    2.12
    ĻĤ
    2.11
    Ļ
    2.01
    uring
    1.99
    Ĩ
    1.98
    ĺ
    1.96
    ¥
    1.82
    Activations Density 0.014%

    No Known Activations