© 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. 30098
    Prev
    Next
    INDEX
    Explanations

    references to contact information and communication details

    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
    +0.17
    1.0%
    419
    +0.17
    1.0%
    63
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.17
    0.06
    213
    +0.17
    0.06
    222
    +0.15
    0.06
    Negative Logits
    ickets
    -1.92
    ths
    -1.77
    itage
    -1.46
     Republic
    -1.39
    strous
    -1.36
     Miranda
    -1.33
    CK
    -1.29
    album
    -1.29
    thro
    -1.28
    Aut
    -1.26
    POSITIVE LOGITS
    href
    1.59
    §
    1.58
    .]
    1.50
    [/
    1.43
    .*]{}
    1.37
    .**]{}
    1.36
    *]{},
    1.36
    .',
    1.35
    quet
    1.33
    iella
    1.32
    Activations Density 3.987%

    No Known Activations