© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 23311
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or phrases related to challenges and struggles

    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
    139
    +0.13
    0.7%
    498
    +0.11
    0.6%
    153
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    452
    +0.13
    0.03
    420
    +0.11
    0.04
    86
    +0.11
    0.03
    Negative Logits
    case
    -1.58
    assic
    -1.55
     case
    -1.53
    orned
    -1.51
    ropolis
    -1.50
    olev
    -1.48
    eral
    -1.48
    raiser
    -1.47
    onomy
    -1.45
    continued
    -1.44
    POSITIVE LOGITS
    ļ
    2.43
    º
    2.06
    ĻĤ
    2.04
    ª
    2.00
    ±
    1.95
    °
    1.92
    ¹
    1.90
    ¬
    1.90
    Ń
    1.88
    ŀ
    1.83
    Activations Density 0.216%

    No Known Activations