© 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. 0-MLP-SM
    11. 27221
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Cort."

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    276
    +0.14
    0.8%
    451
    +0.14
    0.8%
    113
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    451
    +0.14
    0.01
    276
    +0.14
    0.01
    111
    +0.12
    0.01
    Negative Logits
    ľĵ
    -2.50
    µ
    -2.39
    ĵ
    -2.29
    ¶
    -2.29
    ·¸
    -2.18
    ³
    -2.16
    Īĺ
    -2.16
    ¼
    -2.15
    Ń
    -2.15
    ĸ´
    -2.13
    POSITIVE LOGITS
     listener
    1.93
    bara
    1.71
    selves
    1.65
     listeners
    1.56
     pause
    1.50
     stride
    1.49
     backdrop
    1.46
    sa
    1.45
     pointing
    1.43
     Time
    1.36
    Activations Density 0.138%

    No Known Activations