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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 27111
    Prev
    Next
    INDEX
    Explanations

    references to authority figures and their positions in historical or religious contexts

    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
    156
    +0.18
    1.0%
    23
    +0.14
    0.8%
    94
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.18
    0.04
    151
    +0.14
    0.08
    450
    +0.12
    0.07
    Negative Logits
    ¼
    -2.75
    ĥ½
    -2.41
    ħ
    -2.37
    Ģ
    -2.29
    ĻĤ
    -2.27
    ´
    -2.26
    ±
    -2.26
    £
    -2.25
    ©
    -2.19
    Ĺ
    -2.17
    POSITIVE LOGITS
    soever
    1.49
     waiting
    1.40
    ]}$
    1.40
     goodbye
    1.37
    >>
    1.37
     sanity
    1.37
     verification
    1.34
    ]$
    1.32
    rbrack
    1.32
     tolerance
    1.31
    Activations Density 1.819%

    No Known Activations