© 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. 28405
    Prev
    Next
    INDEX
    Explanations

    references to small or miniature objects or concepts

    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
    +0.16
    0.9%
    452
    +0.13
    0.7%
    94
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    452
    +0.16
    0.02
    94
    +0.13
    0.02
    40
    +0.12
    0.02
    Negative Logits
     slightest
    -1.85
    ries
    -1.77
    alus
    -1.76
    orems
    -1.69
    rapeut
    -1.52
     same
    -1.50
    odor
    -1.49
     researchers
    -1.43
    rops
    -1.42
    leftarrow
    -1.39
    POSITIVE LOGITS
    atures
    2.15
    "}](#
    2.02
    ature
    1.79
    ifest
    1.77
    atur
    1.76
    eral
    1.65
    asses
    1.65
    agem
    1.61
    erals
    1.60
    istry
    1.59
    Activations Density 0.131%

    No Known Activations