© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 25856
    Prev
    Next
    INDEX
    Explanations

    Java import statements for various classes and libraries

    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%
    475
    +0.12
    0.7%
    10
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.13
    0.06
    475
    +0.12
    0.05
    498
    +0.12
    0.05
    Negative Logits
     %>
    -1.90
    '));
    -1.73
    '))
    -1.70
    ()</
    -1.67
     parl
    -1.67
    '>
    -1.67
    ');
    -1.65
    iph
    -1.61
    ygen
    -1.54
    ')$
    -1.52
    POSITIVE LOGITS
    ĻĤ
    2.58
    ¿½
    2.39
    Ĩ
    2.33
    Ħ
    2.30
    ĭ
    2.29
    ı
    2.27
    ĵ
    2.23
    Ĥ¬
    2.23
    İ
    2.16
    ¦
    2.14
    Activations Density 0.071%

    No Known Activations