© 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. 29098
    Prev
    Next
    INDEX
    Explanations

    references to devices and device-related terms

    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
    397
    +0.19
    1.1%
    376
    +0.12
    0.7%
    435
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.19
    0.01
    91
    +0.12
    0.01
    435
    +0.11
    0.01
    Negative Logits
     why
    -1.80
     its
    -1.69
     forth
    -1.60
    paces
    -1.59
    ights
    -1.59
    sed
    -1.56
     certain
    -1.54
    ?).
    -1.54
    sing
    -1.52
    hip
    -1.52
    POSITIVE LOGITS
    ieux
    2.17
    iverse
    1.83
    otti
    1.80
    illon
    1.75
    zilla
    1.74
    illac
    1.67
     era
    1.66
    ordo
    1.62
    fileID
    1.57
    vist
    1.55
    Activations Density 0.081%

    No Known Activations