© 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. 23565
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and technical structures

    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
    23
    +0.23
    1.3%
    156
    +0.18
    1.0%
    127
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.23
    0.05
    63
    +0.18
    0.07
    93
    +0.13
    0.09
    Negative Logits
    ĻĤ
    -3.99
    ¶
    -2.78
    ĥ½
    -2.69
    Īĺ
    -2.61
    Ī
    -2.61
    Ĩ
    -2.60
    µ
    -2.59
    ¸
    -2.52
    č↵č↵
    -2.51
    ↵
    -2.51
    POSITIVE LOGITS
    ';
    1.75
    '}
    1.56
     loser
    1.54
     keeper
    1.53
    ');
    1.51
    deal
    1.45
    hips
    1.44
    ')
    1.42
     LORD
    1.42
     streak
    1.39
    Activations Density 2.295%

    No Known Activations