© 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. 26002
    Prev
    Next
    INDEX
    Explanations

    terms related to legal concepts and regulations

    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
    163
    +0.13
    0.7%
    475
    +0.10
    0.6%
    452
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    163
    +0.13
    0.02
    120
    +0.10
    0.02
    475
    +0.10
    0.02
    Negative Logits
     ever
    -1.58
     lately
    -1.56
    iph
    -1.47
     creation
    -1.42
    requently
    -1.38
     infertility
    -1.38
    '),
    -1.38
    ')$
    -1.38
    ospor
    -1.37
    .).
    -1.37
    POSITIVE LOGITS
     halves
    1.43
    UGH
    1.41
     perturbed
    1.40
     unfolded
    1.39
     Adm
    1.35
     Than
    1.35
    ]:
    1.34
     sexes
    1.34
     Forces
    1.32
     Industries
    1.29
    Activations Density 0.035%

    No Known Activations