© 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. 27124
    Prev
    Next
    INDEX
    Explanations

    mentions of DNA and related topics

    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
    91
    +0.13
    0.7%
    156
    +0.10
    0.6%
    93
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    91
    +0.13
    0.02
    93
    +0.10
    0.01
    422
    +0.10
    0.01
    Negative Logits
    §
    -3.02
    ¯
    -3.02
    ³
    -2.88
    ĸ´
    -2.88
    ĭ
    -2.83
    ¼
    -2.78
    Į
    -2.75
    ½
    -2.67
    Ŀ
    -2.62
    ĥ½
    -2.60
    POSITIVE LOGITS
    ISPR
    1.63
    \$
    1.60
    ome
    1.60
    ocene
    1.49
    CHA
    1.46
     follows
    1.45
    Into
    1.45
    ENT
    1.45
    igent
    1.43
    INS
    1.41
    Activations Density 0.639%

    No Known Activations