© 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 EvalsExportsAPI 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. 29335
    Prev
    Next
    INDEX
    Explanations

    the word "also" appearing multiple times in the text

    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
    318
    +0.13
    0.7%
    438
    +0.13
    0.7%
    250
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    318
    +0.13
    0.10
    199
    +0.13
    0.10
    14
    +0.13
    0.09
    Negative Logits
    Ģ
    -2.67
    ģ
    -2.35
    »¿
    -2.35
    ħ
    -2.32
    ¬
    -2.31
    ĩ
    -2.21
    Ħ
    -2.21
    İ
    -2.17
    ľĵ
    -2.16
    ½
    -2.11
    POSITIVE LOGITS
    ?’
    1.48
    )|^
    1.47
    comings
    1.42
    bsd
    1.39
     COUN
    1.37
    Court
    1.35
    remia
    1.35
    ocytosis
    1.34
    ché
    1.34
    =”
    1.29
    Activations Density 0.703%

    No Known Activations