© 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. 27906
    Prev
    Next
    INDEX
    Explanations

    occurrences of the substring "ins."

    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
    250
    +0.14
    0.8%
    434
    +0.13
    0.7%
    90
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    167
    +0.14
    0.02
    90
    +0.13
    0.02
    53
    +0.11
    0.02
    Negative Logits
    Ĭ
    -1.90
    ear
    -1.77
    ĭ
    -1.77
    §
    -1.74
    Ĥ
    -1.71
    »
    -1.71
    ĥ
    -1.68
    Ķ
    -1.66
    tet
    -1.64
    Ħ
    -1.64
    POSITIVE LOGITS
    urances
    1.94
     charge
    1.56
    ulators
    1.55
     Charge
    1.46
    holes
    1.42
    pective
    1.42
    omnia
    1.41
    urrection
    1.39
    ensibly
    1.39
    cribed
    1.36
    Activations Density 4.757%

    No Known Activations