© 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. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 24457
    Prev
    Next
    INDEX
    Explanations

    coded messages and console log statements

    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
    49
    +0.13
    0.7%
    34
    +0.12
    0.7%
    364
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    210
    +0.13
    0.02
    68
    +0.12
    0.05
    424
    +0.11
    0.04
    Negative Logits
    athi
    -1.75
    ricular
    -1.69
    irection
    -1.58
    mal
    -1.56
    pless
    -1.56
    roph
    -1.52
    redited
    -1.51
    YRIGHT
    -1.49
    rant
    -1.48
    amic
    -1.41
    POSITIVE LOGITS
    İ
    2.16
    ¥
    2.09
    ģ
    2.06
    ¹
    2.03
    ħ
    1.97
    Ĥ
    1.97
    ¾
    1.96
    ¤
    1.89
    §
    1.89
    ı
    1.88
    Activations Density 0.293%

    No Known Activations