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

    Neuronpedia

    Jacobian LensNEW
    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. 24728
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 'Q' in various 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
    +0.64
    6.7%
    111
    +0.61
    6.3%
    425
    +0.07
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    415
    +0.64
    0.01
    425
    +0.61
    0.01
    444
    +0.07
    0.00
    Negative Logits
    ↵↵
    -2.08
    <|outofrange|>
    -2.08
             ↵
    -2.08
    č↵
    -2.08
    <|outofrange|>
    -2.08
    ↵
    -2.08
    ↵
    -2.08
    ↵↵
    -2.08
    č↵
    -2.08
    <|outofrange|>
    -2.08
    POSITIVE LOGITS
    ied
    1.10
    ching
    1.07
    iang
    1.01
    reb
    1.01
    cher
    1.00
    PING
    0.99
    enzyme
    0.99
    ijer
    0.99
     envy
    0.99
    iginally
    0.95
    Activations Density 0.033%

    No Known Activations