© 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. 26080
    Prev
    Next
    INDEX
    Explanations

    phrases related to data processing and connections in a structured format

    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
    489
    +0.15
    0.8%
    70
    +0.13
    0.7%
    466
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.15
    0.08
    466
    +0.13
    0.11
    362
    +0.12
    0.07
    Negative Logits
    ĻĤ
    -2.80
    »¿
    -1.82
    Ļª
    -1.75
    ¿½
    -1.70
     Basketball
    -1.63
     MLB
    -1.61
     NBA
    -1.59
     manually
    -1.52
    į
    -1.51
     minors
    -1.46
    POSITIVE LOGITS
    ,’
    1.60
    break
    1.57
    isted
    1.57
    .’
    1.54
     closure
    1.51
    ’.
    1.49
    ’,
    1.47
    ()</
    1.41
    asm
    1.40
    !’
    1.39
    Activations Density 1.549%

    No Known Activations