© 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. 11187
    Prev
    Next
    INDEX
    Explanations

    references to the action of deleting items or data

    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
    156
    +0.22
    1.3%
    25
    +0.12
    0.7%
    239
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    239
    +0.22
    0.03
    148
    +0.12
    0.00
    389
    +0.12
    0.03
    Negative Logits
    "}](#
    -1.96
    lett
    -1.83
    usement
    -1.80
    rie
    -1.65
    éri
    -1.63
    urity
    -1.60
    reo
    -1.59
    ther
    -1.59
    iento
    -1.55
    liest
    -1.51
    POSITIVE LOGITS
    ables
    2.00
    able
    1.80
     dates
    1.64
    InstanceState
    1.57
    Rows
    1.52
    Records
    1.52
     records
    1.48
    msgstr
    1.48
     date
    1.43
     paperwork
    1.43
    Activations Density 0.202%

    No Known Activations