© 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. MLP Post
    5. 2-MLP-SM
    6. 25817
    Prev
    Next
    INDEX
    Explanations

    instances of negative sentiment and pessimistic language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-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_mlp_out
    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
    469
    +0.17
    1.0%
    13
    +0.12
    0.7%
    177
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.17
    0.08
    177
    +0.12
    0.03
    441
    +0.12
    0.02
    Negative Logits
    duced
    -1.55
    Expected
    -1.43
    Generated
    -1.42
    otyped
    -1.41
    specified
    -1.40
     xmlns
    -1.40
     existing
    -1.39
    graded
    -1.39
    mounted
    -1.37
    case
    -1.36
    POSITIVE LOGITS
    ŀ
    1.83
    Ļ
    1.66
    ¬
    1.65
     yards
    1.60
    stown
    1.59
    Ĵ
    1.53
    Äģr
    1.50
    Ŀ
    1.48
    µ
    1.45
    ĸ
    1.42
    Activations Density 1.887%

    No Known Activations