© 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. 0-MLP-SM
    11. 27232
    Prev
    Next
    INDEX
    Explanations

    terms related to official classifications or labels

    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
    156
    +0.19
    1.1%
    376
    +0.18
    1.0%
    470
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    470
    +0.19
    0.01
    277
    +0.18
    0.01
    232
    +0.14
    0.01
    Negative Logits
    ikh
    -1.80
    omorphisms
    -1.63
    omorphism
    -1.60
    uality
    -1.54
    ened
    -1.52
    onas
    -1.45
     coached
    -1.44
     attended
    -1.42
    yle
    -1.42
      ↵
    -1.41
    POSITIVE LOGITS
    fix
    1.70
     Transit
    1.66
     Parenthood
    1.56
    pulse
    1.40
     office
    1.36
    etect
    1.34
    drop
    1.34
     Airport
    1.32
    office
    1.32
    fault
    1.31
    Activations Density 0.011%

    No Known Activations