© 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. 26121
    Prev
    Next
    INDEX
    Explanations

    discussions about social justice and systemic inequalities

    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
    347
    +0.14
    0.8%
    147
    +0.13
    0.8%
    296
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.14
    0.13
    266
    +0.13
    0.01
    250
    +0.10
    0.08
    Negative Logits
     buff
    -1.61
    *(
    -1.49
    hips
    -1.42
     '$
    -1.41
     {}
    -1.41
    ights
    -1.41
    oso
    -1.40
     reb
    -1.39
     spectrum
    -1.38
     freeze
    -1.36
    POSITIVE LOGITS
    ↵
    3.51
    3.51
    <|outofrange|>
    3.51
    3.51
    ↵↵
    3.51
    ↵            ↵
    3.51
    <|padding|>
    3.51
    <|outofrange|>
    3.51
    <|outofrange|>
    3.51
    3.51
    Activations Density 3.191%

    No Known Activations