© 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. 26825
    Prev
    Next
    INDEX
    Explanations

    references to branding and brand development

    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
    406
    +0.12
    0.7%
    157
    +0.11
    0.6%
    449
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    51
    +0.12
    0.01
    33
    +0.11
    0.02
    113
    +0.11
    0.01
    Negative Logits
    fare
    -1.99
    jour
    -1.63
    creas
    -1.60
    osome
    -1.54
    ield
    -1.50
    orage
    -1.47
    iels
    -1.47
    itable
    -1.46
     Clerk
    -1.46
    bserver
    -1.45
    POSITIVE LOGITS
    ĸ
    3.04
    »
    2.94
    Ķ
    2.90
    ¼
    2.86
    ĭ
    2.83
    ·¸
    2.83
    į
    2.83
    ¡
    2.80
    ¿½
    2.79
    ½
    2.78
    Activations Density 0.020%

    No Known Activations