© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 23403
    Prev
    Next
    INDEX
    Explanations

    clauses related to legal definitions and conditions

    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
    427
    +0.12
    0.7%
    126
    +0.11
    0.6%
    321
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.12
    0.14
    499
    +0.11
    0.07
    168
    +0.11
    0.10
    Negative Logits
    ']);
    -1.59
    raise
    -1.51
    '),
    -1.48
    '));
    -1.44
    .'
    -1.43
    ');
    -1.43
    '):
    -1.43
    '.
    -1.41
    %).
    -1.40
     purposes
    -1.40
    POSITIVE LOGITS
    ¸
    2.68
    ©
    2.46
    Į
    2.40
    ·¸
    2.29
    İ
    2.25
    ij
    2.25
    Ĵ
    2.22
    Ń
    2.16
    ¼
    2.09
    ·
    2.09
    Activations Density 3.441%

    No Known Activations