© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 28115
    Prev
    Next
    INDEX
    Explanations

    dates and years associated with events or statistics

    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
    313
    +0.16
    0.9%
    442
    +0.14
    0.8%
    479
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.13
    71
    +0.14
    0.16
    156
    +0.13
    0.16
    Negative Logits
     alone
    -1.57
    infty
    -1.48
    sembles
    -1.43
     indoors
    -1.42
     lado
    -1.42
     ranch
    -1.42
     Estate
    -1.42
    blockList
    -1.37
    falls
    -1.36
     ::
    -1.35
    POSITIVE LOGITS
    }}</
    1.72
    CDATA
    1.56
     improvement
    1.42
    )</
    1.40
    '''
    1.39
     Univ
    1.36
    ]]
    1.36
     career
    1.35
    ]."
    1.33
    ogue
    1.33
    Activations Density 3.920%

    No Known Activations