© 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. 26539
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to average and typical metrics or values

    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
    266
    +0.11
    0.6%
    351
    +0.11
    0.6%
    461
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    14
    +0.11
    0.03
    407
    +0.11
    0.03
    118
    +0.10
    0.03
    Negative Logits
     care
    -1.76
    ANT
    -1.65
    ittal
    -1.63
     value
    -1.43
    ital
    -1.42
    lass
    -1.38
    ITAL
    -1.38
    amental
    -1.38
     homem
    -1.37
    anches
    -1.36
    POSITIVE LOGITS
     Cemetery
    1.42
    ureus
    1.42
    ropolis
    1.40
    ^](#
    1.35
     "_
    1.34
     Palestine
    1.34
    chester
    1.34
     ],
    1.33
     ("[
    1.32
    rawl
    1.30
    Activations Density 0.428%

    No Known Activations