© 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. Residuals
    9. 4-RES-SM
    11. 12927
    Prev
    Next
    INDEX
    Explanations

    instances of the word "randomly" and its variations, indicating a focus on randomness or chance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.16
    0.9%
    21
    +0.16
    0.9%
    477
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    202
    +0.16
    0.00
    78
    +0.16
    -0.00
    375
    +0.14
    0.01
    Negative Logits
    ivism
    -1.64
    ibility
    -1.54
     history
    -1.52
     generality
    -1.48
    disambiguation
    -1.40
    uality
    -1.39
     presence
    -1.38
     seriousness
    -1.37
    ly
    -1.37
     expression
    -1.36
    POSITIVE LOGITS
     assigned
    1.93
    ·
    1.92
     allocated
    1.89
    ↵↵
    1.84
    1.84
    ↵
    1.84
    <|outofrange|>
    1.84
    ↵        ↵
    1.84
    <|outofrange|>
    1.84
    ↵
    1.84
    Activations Density 0.043%

    No Known Activations