© 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. 26813
    Prev
    Next
    INDEX
    Explanations

    the phrase "within 10"

    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
    119
    +0.14
    0.8%
    480
    +0.13
    0.7%
    207
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.14
    0.04
    82
    +0.13
    0.04
    112
    +0.11
    0.04
    Negative Logits
    onomic
    -1.65
    ”,
    -1.49
    ”),
    -1.46
    ”)
    -1.42
    '],
    -1.41
    ifen
    -1.41
    ige
    -1.41
    ']);
    -1.39
    inin
    -1.38
    rowing
    -1.37
    POSITIVE LOGITS
     reads
    1.67
    etheus
    1.48
    NESS
    1.39
     thro
    1.39
     minds
    1.38
    dling
    1.34
    thia
    1.34
    zza
    1.33
     lives
    1.31
    ious
    1.31
    Activations Density 0.022%

    No Known Activations