© 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. 26907
    Prev
    Next
    INDEX
    Explanations

    the frequency of "to" and "their" in directives or obligations

    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
    64
    +0.14
    0.8%
    244
    +0.11
    0.6%
    34
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.14
    0.37
    151
    +0.11
    0.31
    434
    +0.10
    0.29
    Negative Logits
    letons
    -1.94
     oath
    -1.76
    ^**
    -1.70
    **^
    -1.62
     **(
    -1.60
    blogspot
    -1.54
    **.
    -1.53
    *>(
    -1.50
    "}](
    -1.50
    endl
    -1.48
    POSITIVE LOGITS
    »
    2.14
    Ļª
    1.95
    ¼
    1.93
    ĨĴ
    1.92
    ļ
    1.90
    ·
    1.85
    į
    1.82
    Ħ
    1.81
    ĺ
    1.75
    ¿½
    1.72
    Activations Density 1.774%

    No Known Activations