© 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. 27689
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sign."

    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
    59
    +0.13
    0.7%
    172
    +0.11
    0.6%
    376
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    126
    +0.13
    0.02
    243
    +0.11
    0.01
    59
    +0.10
    0.01
    Negative Logits
    undry
    -1.64
    ")]
    -1.59
     thee
    -1.54
    '))
    -1.51
    laid
    -1.50
    '));
    -1.50
    '>
    -1.49
    rian
    -1.43
    "));
    -1.43
    AndroidRuntime
    -1.40
    POSITIVE LOGITS
    ĩ
    2.00
    ored
    1.89
    ificantly
    1.87
    orable
    1.86
    ĻĤ
    1.72
    bugs
    1.63
     submissions
    1.56
    stones
    1.46
    orest
    1.46
    rams
    1.45
    Activations Density 0.903%

    No Known Activations