© 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. 26465
    Prev
    Next
    INDEX
    Explanations

    terms related to technical and digital contexts

    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
    320
    +0.14
    0.8%
    3
    +0.11
    0.6%
    80
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    347
    +0.14
    0.06
    332
    +0.11
    0.07
    456
    +0.10
    0.00
    Negative Logits
    ic
    -1.82
    ander
    -1.73
    onies
    -1.68
    esar
    -1.58
    icum
    -1.58
    ires
    -1.55
    cean
    -1.53
    ec
    -1.49
    inis
    -1.49
    ceans
    -1.49
    POSITIVE LOGITS
     surprise
    1.73
     deform
    1.58
     objection
    1.56
     complication
    1.54
     defect
    1.53
    ^âĪĴ
    1.48
     fright
    1.48
    ault
    1.48
     shoulder
    1.45
     refractory
    1.44
    Activations Density 1.828%

    No Known Activations