© 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. 2-MLP-SM
    11. 22558
    Prev
    Next
    INDEX
    Explanations

    instances of various characters and their roles in narratives

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    23
    +0.20
    1.1%
    345
    +0.12
    0.7%
    79
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    180
    +0.20
    0.03
    23
    +0.12
    0.02
    411
    +0.11
    0.02
    Negative Logits
    eno
    -1.96
    ford
    -1.86
    oku
    -1.70
    enium
    -1.60
    rapeut
    -1.56
    ettes
    -1.54
    enos
    -1.46
    doors
    -1.44
    ableness
    -1.44
    boro
    -1.43
    POSITIVE LOGITS
    ĥ½
    2.75
    ¿
    2.36
    ·¸
    2.33
    ¦
    2.31
    ²
    2.28
    µ
    2.27
    ¿½
    2.24
    ·
    2.20
    ĸ´
    2.18
    ³
    2.17
    Activations Density 0.429%

    No Known Activations