© 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. 26501
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" 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
    176
    +0.15
    0.9%
    150
    +0.13
    0.7%
    22
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    92
    +0.15
    0.12
    150
    +0.13
    0.13
    22
    +0.13
    0.11
    Negative Logits
    ert
    -1.78
    "}](#
    -1.69
    ibr
    -1.47
    sey
    -1.39
    ose
    -1.36
    OTH
    -1.35
    ity
    -1.34
    cient
    -1.34
    ateness
    -1.33
    ichlor
    -1.33
    POSITIVE LOGITS
    ĻĤ
    2.81
    ľĵ
    2.52
    2.35
             ↵
    2.35
    2.35
           ↵
    2.35
    ↵
    2.35
    ↵
    2.35
    <|outofrange|>
    2.35
     ↵
    2.35
    Activations Density 1.489%

    No Known Activations