© 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. 30023
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or critiques

    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
    97
    +0.14
    0.8%
    452
    +0.14
    0.8%
    203
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    97
    +0.14
    0.07
    452
    +0.14
    0.05
    203
    +0.13
    0.07
    Negative Logits
    isp
    -1.85
    80211
    -1.83
    -"
    -1.75
    uild
    -1.66
    inctions
    -1.64
    utively
    -1.63
    ynamic
    -1.61
    icit
    -1.61
    etically
    -1.60
    ILITY
    -1.60
    POSITIVE LOGITS
    ¸
    2.82
    ´
    2.68
    ī
    2.67
    ·
    2.55
    Ĥ
    2.51
    ©
    2.48
    ¹
    2.34
    Ħ
    2.31
    ¾
    2.31
    ®
    2.30
    Activations Density 0.286%

    No Known Activations