© 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. 26573
    Prev
    Next
    INDEX
    Explanations

    phrases indicating dependency or reliance in various 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
    108
    +0.15
    0.8%
    225
    +0.13
    0.7%
    14
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    14
    +0.15
    0.07
    404
    +0.13
    0.06
    88
    +0.10
    0.06
    Negative Logits
     `
    -1.70
    ]{.
    -1.60
     *[
    -1.54
     "`
    -1.49
     unfolding
    -1.44
    ility
    -1.43
     ![
    -1.43
     *
    -1.42
    sever
    -1.41
     simplicity
    -1.40
    POSITIVE LOGITS
    EEK
    1.67
    oxford
    1.51
    Getty
    1.46
    ĵ
    1.44
    lickr
    1.44
     soit
    1.41
     deserves
    1.38
    azioni
    1.35
    ↵↵
    1.34
    1.34
    Activations Density 0.415%

    No Known Activations