© 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. 0-MLP-SM
    11. 30286
    Prev
    Next
    INDEX
    Explanations

    multiple instances of the word 'ere'

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    258
    +0.12
    0.7%
    376
    +0.12
    0.7%
    77
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.12
    0.01
    77
    +0.12
    0.01
    476
    +0.11
    0.01
    Negative Logits
    olerance
    -1.69
     warn
    -1.57
    "];
    -1.55
     say
    -1.50
    ArgumentException
    -1.49
    over
    -1.44
    ");
    -1.44
    ushed
    -1.44
    oler
    -1.44
    here
    -1.43
    POSITIVE LOGITS
    bellum
    1.95
    ½
    1.90
    prises
    1.84
    bilt
    1.83
    ÅĽci
    1.78
    bank
    1.77
    bies
    1.69
    bbe
    1.69
    bels
    1.64
    ĻĤ
    1.63
    Activations Density 0.021%

    No Known Activations