Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27724
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Del"

    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
    369
    +0.19
    1.1%
    477
    +0.12
    0.6%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    90
    +0.19
    0.02
    348
    +0.12
    0.02
    401
    +0.11
    0.02
    Negative Logits
    COP
    -1.80
    remia
    -1.47
    response
    -1.47
    acial
    -1.39
    ession
    -1.37
    holding
    -1.35
    ternal
    -1.32
    ROS
    -1.30
    cluding
    -1.29
    OPLE
    -1.28
    POSITIVE LOGITS
    ©
    2.40
    ĻĤ
    2.16
    ®
    2.13
    º
    2.01
    leys
    1.93
    orian
    1.78
    ĨĴ
    1.68
    gate
    1.67
    ayed
    1.65
    antine
    1.64
    Activations Density 1.043%

    No Known Activations