© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 25932
    Prev
    Next
    INDEX
    Explanations

    words ending in "er"

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    23
    +0.18
    1.1%
    377
    +0.13
    0.7%
    271
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.18
    0.04
    377
    +0.13
    0.04
    141
    +0.12
    0.05
    Negative Logits
    ī
    -2.75
    Ī
    -2.40
    ¯
    -2.36
    ¬
    -2.27
    ²
    -2.26
    ľ
    -2.25
    ı
    -2.21
    ķ
    -2.19
    ¤
    -2.19
    ½
    -2.18
    POSITIVE LOGITS
    STEM
    1.66
    forall
    1.57
    áŁ
    1.54
    Tube
    1.54
    odot
    1.48
     thankful
    1.44
    circ
    1.41
    áĥĶáĥ
    1.40
    idyl
    1.39
     COPYRIGHT
    1.39
    Activations Density 0.448%

    No Known Activations