© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 12289
    Prev
    Next
    INDEX
    Explanations

    terms related to electrical concepts and devices

    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
    +0.15
    0.9%
    306
    +0.13
    0.8%
    507
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.15
    0.02
    507
    +0.13
    0.02
    253
    +0.13
    0.03
    Negative Logits
     respect
    -1.80
    head
    -1.59
    quel
    -1.55
    erve
    -1.54
    dehy
    -1.49
    heads
    -1.48
    hoe
    -1.47
    iley
    -1.44
    unnumbered
    -1.43
    ULT
    -1.43
    POSITIVE LOGITS
    rifying
    2.91
    romagnetic
    2.86
    rified
    2.82
    rification
    2.75
    rical
    2.67
    rically
    2.53
    romy
    2.39
    rone
    2.35
    rophys
    2.33
    rophot
    2.32
    Activations Density 0.110%

    No Known Activations