© 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. 0-MLP-SM
    6. 27155
    Prev
    Next
    INDEX
    Explanations

    references to various crises

    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
    156
    +0.35
    2.2%
    376
    +0.10
    0.6%
    8
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.35
    0.01
    311
    +0.10
    0.02
    184
    +0.10
    0.02
    Negative Logits
    edu
    -1.61
    yahoo
    -1.50
    à±
    -1.47
    npmjs
    -1.43
    à¬
    -1.42
    ção
    -1.40
    >'
    -1.39
    tgz
    -1.39
     donated
    -1.36
    inib
    -1.36
    POSITIVE LOGITS
    ously
    2.16
    proof
    1.89
     tolerance
    1.78
    ulent
    1.67
    witz
    1.64
     tone
    1.62
    break
    1.59
     surrounds
    1.58
    atted
    1.57
    ally
    1.53
    Activations Density 0.020%

    No Known Activations