© 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 EvalsExportsAPI 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. 24460
    Prev
    Next
    INDEX
    Explanations

    information related to comprehensive product offerings and technology services

    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
    104
    +0.14
    0.8%
    174
    +0.11
    0.6%
    320
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    120
    +0.14
    0.14
    104
    +0.11
    0.09
    277
    +0.11
    0.12
    Negative Logits
    vance
    -1.48
    iterator
    -1.47
    along
    -1.44
    quiet
    -1.39
    ention
    -1.39
     conveyed
    -1.38
     reminder
    -1.38
     eternity
    -1.32
     trailers
    -1.30
     trailer
    -1.29
    POSITIVE LOGITS
    ĥ½
    1.73
    ozo
    1.56
     sino
    1.55
    haus
    1.51
    theless
    1.51
     Borough
    1.50
     Corps
    1.48
    ī
    1.47
     Equation
    1.45
    ème
    1.43
    Activations Density 1.807%

    No Known Activations