© 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. 10530
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and their results

    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
    +0.23
    1.3%
    397
    +0.15
    0.9%
    136
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.23
    0.00
    136
    +0.15
    0.00
    448
    +0.12
    0.02
    Negative Logits
    stand
    -1.53
    sembles
    -1.41
    .',
    -1.33
    agne
    -1.28
    .[^
    -1.27
    '},
    -1.27
     background
    -1.25
    >;
    -1.21
    all
    -1.21
    imate
    -1.21
    POSITIVE LOGITS
    ¼
    2.34
    ĵ
    2.31
    º
    2.09
    ¬
    2.05
    ĩ
    2.04
    Ĥ¬
    2.04
    ¸
    1.99
    Į
    1.97
    ŀ
    1.89
    »
    1.84
    Activations Density 0.066%

    No Known Activations