© 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. 30384
    Prev
    Next
    INDEX
    Explanations

    the presence of the number 89 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
    81
    +0.15
    0.8%
    458
    +0.13
    0.7%
    350
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    458
    +0.15
    0.02
    199
    +0.13
    0.02
    44
    +0.11
    0.02
    Negative Logits
    ennis
    -1.86
     pity
    -1.69
     condemn
    -1.50
    river
    -1.50
     waste
    -1.48
    sworth
    -1.48
    onia
    -1.43
    "?"
    -1.41
    abouts
    -1.39
     condemnation
    -1.39
    POSITIVE LOGITS
    ¾
    2.69
    ®
    2.57
    Ľ
    2.36
    ģ
    2.31
    ¶
    2.29
    ³
    2.24
    ¨
    2.16
    µ
    2.15
    ¬
    2.12
    Ń
    2.06
    Activations Density 0.019%

    No Known Activations