© 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. 26050
    Prev
    Next
    INDEX
    Explanations

    words related to acidity or acidic content

    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
    156
    +0.17
    1.0%
    23
    +0.16
    0.9%
    390
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.17
    0.02
    332
    +0.16
    0.03
    38
    +0.15
    0.01
    Negative Logits
    quarters
    -1.76
    ),\
    -1.72
    icles
    -1.64
     Published
    -1.59
     =>
    -1.57
    =>
    -1.57
    )',
    -1.56
    }),\
    -1.51
    ition
    -1.47
    ologie
    -1.43
    POSITIVE LOGITS
    Ļª
    4.12
    »¿
    3.90
    ¿½
    3.80
    ª
    3.68
    3.65
    ↵
    3.65
    3.65
       ↵
    3.65
    č↵č↵
    3.65
    <|outofrange|>
    3.65
    Activations Density 0.152%

    No Known Activations