© 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. 26254
    Prev
    Next
    INDEX
    Explanations

    instances of the word "put" in various contexts

    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
    320
    +0.12
    0.7%
    376
    +0.11
    0.6%
    101
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    320
    +0.12
    0.01
    101
    +0.11
    0.01
    427
    +0.10
    0.01
    Negative Logits
    ľ
    -2.67
    ©
    -2.40
    Ĺ
    -2.38
    «
    -2.35
    ¡
    -2.34
    ĵ
    -2.32
    ķ
    -2.31
    ı
    -2.30
    ¿
    -2.17
    Ī
    -2.15
    POSITIVE LOGITS
     pains
    1.81
    bugs
    1.74
    iative
    1.66
    tion
    1.65
    enstein
    1.60
    tering
    1.55
    gres
    1.53
     worries
    1.51
    inib
    1.51
    nik
    1.49
    Activations Density 0.014%

    No Known Activations