© 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. 25973
    Prev
    Next
    INDEX
    Explanations

    instances of clauses introducing conditions or examples

    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
    142
    +0.15
    0.8%
    459
    +0.10
    0.5%
    340
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    423
    +0.15
    0.04
    459
    +0.10
    0.04
    404
    +0.10
    0.04
    Negative Logits
     forth
    -1.53
    acial
    -1.51
    rial
    -1.48
     hats
    -1.45
    ERR
    -1.43
     thick
    -1.40
    stderr
    -1.38
     FITNESS
    -1.38
    irs
    -1.38
    ASP
    -1.37
    POSITIVE LOGITS
     ↵
    2.18
    2.18
    ↵
    2.18
    ↵
    2.18
    ↵↵
    2.18
    2.18
    2.18
    2.18
     ↵
    2.18
    2.18
    Activations Density 0.214%

    No Known Activations