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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 25895
    Prev
    Next
    INDEX
    Explanations

    possessive forms, particularly those related to personal ownership or belonging

    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
    366
    +0.12
    0.7%
    259
    +0.11
    0.6%
    173
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    474
    +0.12
    0.04
    322
    +0.11
    0.04
    38
    +0.11
    0.02
    Negative Logits
    zes
    -1.45
    aph
    -1.45
    's
    -1.43
    atories
    -1.35
    ters
    -1.31
    aint
    -1.28
    ships
    -1.27
    cam
    -1.27
     statistics
    -1.27
     Loss
    -1.26
    POSITIVE LOGITS
    ·¸
    2.38
    Ķ
    2.19
    ©
    2.11
    Ĺ
    2.08
    IJ
    2.05
    ¤
    1.99
    ĥ½
    1.95
    ķ
    1.86
    §
    1.86
    ħ
    1.80
    Activations Density 0.434%

    No Known Activations