© 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. 26486
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'm'

    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
    81
    +0.15
    0.9%
    405
    +0.14
    0.8%
    196
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    405
    +0.15
    0.09
    196
    +0.14
    0.09
    81
    +0.14
    0.08
    Negative Logits
    tered
    -1.81
     authors
    -1.57
     answered
    -1.55
    an
    -1.54
     answer
    -1.46
    pload
    -1.45
    lasses
    -1.41
     reply
    -1.41
    lceil
    -1.37
    terday
    -1.37
    POSITIVE LOGITS
    ène
    1.60
    osph
    1.60
    TOR
    1.58
    plify
    1.56
    endor
    1.52
    istry
    1.51
    houses
    1.46
    ikel
    1.45
    orphic
    1.42
    issions
    1.41
    Activations Density 0.623%

    No Known Activations