© 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 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. 28514
    Prev
    Next
    INDEX
    Explanations

    phrases or terms that describe specific characteristics or features

    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
    380
    +0.16
    0.9%
    149
    +0.13
    0.8%
    376
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    380
    +0.16
    0.01
    149
    +0.13
    0.01
    103
    +0.13
    0.01
    Negative Logits
    ders
    -1.58
    nae
    -1.45
     attracted
    -1.42
    +$
    -1.39
     perfect
    -1.38
    llo
    -1.37
     participants
    -1.31
     presented
    -1.31
    omorphisms
    -1.30
    lang
    -1.30
    POSITIVE LOGITS
    ĻĤ
    1.78
    arily
    1.75
    enso
    1.66
     deleter
    1.65
    £
    1.60
     Parenthood
    1.56
     alia
    1.55
    agon
    1.54
    ostic
    1.53
    agment
    1.52
    Activations Density 0.007%

    No Known Activations