© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 31143
    Prev
    Next
    INDEX
    Explanations

    names of people and locations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    438
    +0.12
    0.7%
    149
    +0.12
    0.7%
    135
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    380
    +0.12
    0.02
    75
    +0.12
    0.02
    390
    +0.12
    0.02
    Negative Logits
    annels
    -1.37
    ermal
    -1.36
    roscopic
    -1.33
    ring
    -1.32
    '?
    -1.30
     choosing
    -1.28
    ensibly
    -1.27
    urity
    -1.27
     view
    -1.26
     Appe
    -1.26
    POSITIVE LOGITS
    onte
    1.84
    ¡
    1.60
    (*
    1.52
    hip
    1.49
     subdivision
    1.44
    Ŀ
    1.44
    *(*
    1.44
    (<
    1.42
    pe
    1.40
    že
    1.40
    Activations Density 1.459%

    No Known Activations