© 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. 26528
    Prev
    Next
    INDEX
    Explanations

    references to licensing terminology, particularly regarding warranties and the GNU General Public License

    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
    77
    +0.12
    0.7%
    479
    +0.12
    0.7%
    497
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    414
    +0.12
    0.01
    318
    +0.12
    0.01
    77
    +0.12
    0.02
    Negative Logits
    PLIED
    -1.38
    PROM
    -1.34
    ETHOD
    -1.32
    RUPT
    -1.31
    link
    -1.30
    ))$.
    -1.29
    gently
    -1.27
    **).
    -1.27
     methylation
    -1.25
    encing
    -1.25
    POSITIVE LOGITS
    ¨
    2.12
    ļ
    2.07
    ª
    2.05
    ħ
    1.99
    ĩ
    1.92
    ĥ
    1.91
    §
    1.88
    ī
    1.76
    ¦
    1.75
    ĭ
    1.70
    Activations Density 0.232%

    No Known Activations