© 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. 26560
    Prev
    Next
    INDEX
    Explanations

    mentions of "the" and other definite articles indicating specificity

    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
    441
    +0.18
    1.0%
    484
    +0.13
    0.8%
    17
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.18
    0.11
    484
    +0.13
    0.07
    368
    +0.13
    0.09
    Negative Logits
    ert
    -1.61
    ]{}
    -1.48
    otta
    -1.43
    [@
    -1.42
     deriving
    -1.38
     [@
    -1.36
    angs
    -1.32
     lowering
    -1.31
    uminous
    -1.30
    zing
    -1.30
    POSITIVE LOGITS
    ĻĤ
    3.44
    Īĺ
    2.95
    Ļ
    2.91
    ľĵ
    2.76
    ¿
    2.73
    «
    2.73
    ģ
    2.67
    2.67
    ↵  âĢĥ
    2.67
    <|outofrange|>
    2.67
    Activations Density 1.105%

    No Known Activations