© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27781
    Prev
    Next
    INDEX
    Explanations

    terms related to the act of administering substances, particularly through injections

    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
    156
    +0.24
    1.4%
    148
    +0.15
    0.9%
    376
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    200
    +0.24
    0.01
    317
    +0.15
    0.01
    344
    +0.14
    0.01
    Negative Logits
     celebrated
    -1.48
    *=
    -1.42
    aned
    -1.38
    illed
    -1.36
    called
    -1.33
    ured
    -1.33
     descended
    -1.30
    lessly
    -1.29
    ming
    -1.28
     dawn
    -1.27
    POSITIVE LOGITS
    imensional
    1.62
     argu
    1.59
    guns
    1.58
    iative
    1.50
     offense
    1.50
    starter
    1.49
    Ģ
    1.47
    nant
    1.47
    ster
    1.43
     wrong
    1.43
    Activations Density 0.007%

    No Known Activations