© 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 EvalsExportsinterp-engineNEWAPI 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. 13848
    Prev
    Next
    INDEX
    Explanations

    terms related to thermal energy or thermal relationships 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__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
    21
    +0.20
    1.2%
    136
    +0.11
    0.6%
    156
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.20
    0.02
    134
    +0.11
    0.05
    59
    +0.10
    0.04
    Negative Logits
    ows
    -1.62
    ensch
    -1.55
    hearted
    -1.50
    iken
    -1.42
     possession
    -1.38
    rowser
    -1.38
    ties
    -1.35
    )];
    -1.33
    eled
    -1.33
    ostream
    -1.32
    POSITIVE LOGITS
    mic
    2.87
    Ļ
    2.78
    m
    2.75
    ľ
    2.62
    Ĵ
    2.59
    mia
    2.58
    mology
    2.58
    ĵ
    2.52
    ij
    2.49
    Ģ
    2.40
    Activations Density 0.468%

    No Known Activations