© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26005
    Prev
    Next
    INDEX
    Explanations

    the word "carried" and its variations 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
    203
    +0.13
    0.7%
    12
    +0.13
    0.7%
    20
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    433
    +0.13
    0.02
    263
    +0.13
    0.03
    185
    +0.11
    0.02
    Negative Logits
    ¢
    -3.79
    Īĺ
    -3.77
    ĻĤ
    -3.42
    Ĺ
    -3.41
    Ŀ
    -3.33
    ŀ
    -3.30
    ķ
    -3.24
    ģ
    -3.22
    ¨
    -3.21
    ¯
    -3.19
    POSITIVE LOGITS
     dealer
    1.48
     Telesc
    1.44
     Design
    1.39
    ÂĴ
    1.38
     adv
    1.36
     exhib
    1.34
    estock
    1.33
     Reviews
    1.32
     Caption
    1.31
     IOP
    1.30
    Activations Density 0.418%

    No Known Activations