© 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. 22930
    Prev
    Next
    INDEX
    Explanations

    phrases related to permission and actions related to copying and distributing content

    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
    134
    +0.15
    0.8%
    23
    +0.12
    0.6%
    55
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.15
    0.02
    67
    +0.12
    0.03
    120
    +0.11
    0.03
    Negative Logits
    rpm
    -1.86
    idade
    -1.81
     rpm
    -1.70
    \]\].
    -1.60
    bie
    -1.54
    idades
    -1.54
    arus
    -1.53
    ĻĤ
    -1.51
    meg
    -1.51
    ahan
    -1.50
    POSITIVE LOGITS
    ĩ
    1.91
    acea
    1.65
     intercept
    1.56
    ĥ
    1.54
    prevent
    1.45
    ische
    1.44
    gets
    1.41
    reated
    1.40
    ½
    1.37
     transitions
    1.37
    Activations Density 0.258%

    No Known Activations