© 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. 26770
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the character 'b' 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
    478
    +0.21
    1.2%
    156
    +0.21
    1.2%
    23
    +0.21
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    395
    +0.21
    0.02
    111
    +0.21
    0.01
    410
    +0.21
    0.01
    Negative Logits
     Ltd
    -2.05
    ional
    -1.77
    aje
    -1.76
    amiento
    -1.73
    naire
    -1.68
    ally
    -1.64
    isme
    -1.63
    ismo
    -1.63
    ÅĽci
    -1.60
    usta
    -1.58
    POSITIVE LOGITS
    ĨĴ
    2.95
    Īĺ
    2.91
    «
    2.91
    ĸ´
    2.90
    ĥ
    2.87
    ĻĤ
    2.86
    ²
    2.83
    Ĵ
    2.79
    ©
    2.78
    Ĥ¬
    2.77
    Activations Density 0.266%

    No Known Activations