© 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. 25965
    Prev
    Next
    INDEX
    Explanations

    financial terms and references to specific dates or periods

    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
    420
    +0.13
    0.7%
    159
    +0.13
    0.7%
    511
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    420
    +0.13
    0.09
    511
    +0.13
    0.05
    79
    +0.12
    0.09
    Negative Logits
     percentile
    -1.48
     encodes
    -1.42
    \]](
    -1.40
     iff
    -1.39
     habÃŃa
    -1.39
     estaba
    -1.37
    tait
    -1.35
    ÃŃa
    -1.34
     specializes
    -1.31
    ogg
    -1.29
    POSITIVE LOGITS
     Ont
    1.73
     brow
    1.54
    ities
    1.46
    atics
    1.45
     developers
    1.38
     Scot
    1.36
     governing
    1.32
    liness
    1.30
    atives
    1.29
    eful
    1.29
    Activations Density 1.573%

    No Known Activations