© 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. 2-RES-SM
    6. 12329
    Prev
    Next
    INDEX
    Explanations

    variables and parameters in a programming context

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    121
    +0.17
    1.0%
    143
    +0.15
    0.8%
    302
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    143
    +0.17
    0.09
    67
    +0.15
    0.05
    121
    +0.13
    0.08
    Negative Logits
    [])
    -1.68
     licenses
    -1.60
     forums
    -1.52
    journals
    -1.47
    reon
    -1.43
    ^](#
    -1.42
     textbooks
    -1.41
    notes
    -1.40
    icates
    -1.39
    icating
    -1.35
    POSITIVE LOGITS
    ·¸
    2.29
    ¤
    2.12
    ħ
    2.10
    ī
    2.06
    ¦
    2.06
    »¿
    2.05
    ¶
    2.02
    ³
    2.02
    į
    1.99
    ±
    1.99
    Activations Density 4.583%

    No Known Activations