© 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. 28203
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming or technical specifications

    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
    400
    +0.15
    0.9%
    332
    +0.14
    0.8%
    160
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    96
    +0.15
    0.04
    400
    +0.14
    0.03
    470
    +0.12
    0.18
    Negative Logits
    nae
    -1.92
     whom
    -1.37
     fucked
    -1.36
    nier
    -1.35
    ]{}]{}
    -1.33
    noreply
    -1.33
     answ
    -1.31
    elon
    -1.29
     husbands
    -1.28
     better
    -1.25
    POSITIVE LOGITS
    ĨĴ
    2.05
    ¯
    2.04
    ¦
    2.04
    Į
    2.01
    ł
    1.98
    ľĵ
    1.88
    ļ
    1.79
    Ķ
    1.77
    Ħ
    1.72
    Ł
    1.71
    Activations Density 7.461%

    No Known Activations