© 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. 28656
    Prev
    Next
    INDEX
    Explanations

    the presence of the substring "ENS" 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
    376
    +0.13
    0.8%
    444
    +0.12
    0.7%
    109
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.13
    0.01
    109
    +0.12
    0.01
    77
    +0.12
    0.01
    Negative Logits
    »
    -2.26
    ¼
    -2.08
    ĸ´
    -1.98
    ¾
    -1.94
    Ł
    -1.90
    ĥ½
    -1.89
    ¿½
    -1.88
    ´
    -1.86
    ¹
    -1.85
    ¸
    -1.83
    POSITIVE LOGITS
    ARRAY
    1.91
    dorff
    1.79
    FONT
    1.74
    CRIPT
    1.74
    IVE
    1.71
    ist
    1.66
    URES
    1.64
    ificial
    1.58
    ium
    1.58
    ULAR
    1.56
    Activations Density 0.014%

    No Known Activations