© 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. 28149
    Prev
    Next
    INDEX
    Explanations

    elements related to coding and web development languages

    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
    479
    +0.18
    1.1%
    198
    +0.16
    0.9%
    153
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.18
    0.07
    330
    +0.16
    0.10
    133
    +0.16
    0.07
    Negative Logits
    visiae
    -1.48
     otherwise
    -1.46
    rapeut
    -1.44
     år
    -1.36
     deadlines
    -1.35
    ↵									
    -1.35
    onen
    -1.34
    anos
    -1.34
     prospective
    -1.33
     satisf
    -1.31
    POSITIVE LOGITS
    aby
    1.49
    ESULT
    1.48
    áĢĢ
    1.46
    ashi
    1.41
    ounds
    1.38
    áĢIJ
    1.38
    áĢ
    1.37
    course
    1.34
     marks
    1.33
    àº
    1.33
    Activations Density 3.406%

    No Known Activations