© 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. Residuals
    9. 4-RES-SM
    11. 12101
    Prev
    Next
    INDEX
    Explanations

    Java programming constructs and data structures

    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
    409
    +0.13
    0.7%
    255
    +0.12
    0.7%
    504
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    349
    +0.13
    0.06
    181
    +0.12
    0.07
    357
    +0.12
    0.05
    Negative Logits
    **~
    -1.98
    \)
    -1.84
     ourselves
    -1.81
     ",
    -1.80
     yourselves
    -1.73
    **.
    -1.67
     yourself
    -1.66
     ***
    -1.64
     \(
    -1.60
    **),
    -1.57
    POSITIVE LOGITS
    ;
    2.98
    .*;
    2.67
    ;_
    2.41
    ;}
    2.15
    Utils
    2.08
    *;
    2.07
    Listener
    2.03
    >();
    2.01
    Factory
    2.01
    Constants
    1.99
    Activations Density 0.373%

    No Known Activations