© 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. 2-MLP-SM
    11. 24900
    Prev
    Next
    INDEX
    Explanations

    references to computer operating systems, software, and programming environments

    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
    34
    +0.12
    0.6%
    79
    +0.11
    0.6%
    373
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    79
    +0.12
    0.03
    8
    +0.11
    0.03
    417
    +0.11
    0.03
    Negative Logits
     yours
    -1.78
    longrightarrow
    -1.57
    irez
    -1.56
     extinct
    -1.53
    ERIAL
    -1.52
    inae
    -1.45
    documentclass
    -1.42
    blogger
    -1.41
     alia
    -1.39
    topic
    -1.38
    POSITIVE LOGITS
     Went
    1.69
    cy
    1.67
     angles
    1.55
     Commercial
    1.49
    ↵Č
    1.43
     ([
    1.41
     Enforcement
    1.40
     flows
    1.37
     ends
    1.37
     lengths
    1.37
    Activations Density 0.171%

    No Known Activations