© 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. 10980
    Prev
    Next
    INDEX
    Explanations

    nouns related to various geographical locations

    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
    271
    +0.17
    1.0%
    111
    +0.17
    1.0%
    136
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.17
    0.00
    498
    +0.17
    0.07
    491
    +0.14
    0.07
    Negative Logits
     raised
    -1.51
    âĢĤ
    -1.44
     meant
    -1.41
    WF
    -1.37
    arily
    -1.37
     wired
    -1.34
     FIG
    -1.32
     âĢķ
    -1.32
     WE
    -1.32
    âĢħ
    -1.32
    POSITIVE LOGITS
    ensis
    2.06
    aceae
    1.76
    anoi
    1.71
    ennes
    1.63
    inae
    1.59
     sunt
    1.58
    ência
    1.57
    rä
    1.57
    ίαÏĤ
    1.56
     anos
    1.55
    Activations Density 1.095%

    No Known Activations