© 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. 23003
    Prev
    Next
    INDEX
    Explanations

    negative phrases related to the absence or lack of something

    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
    479
    +0.12
    0.7%
    160
    +0.11
    0.6%
    466
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.12
    0.02
    476
    +0.11
    0.06
    470
    +0.10
    0.06
    Negative Logits
    ¿½
    -2.47
    ī
    -2.06
    Ļª
    -2.04
    ©
    -1.95
    Ľ
    -1.95
    ·
    -1.92
    Ĩ
    -1.83
    Ĺ
    -1.79
    ĸ´
    -1.79
    ³
    -1.75
    POSITIVE LOGITS
    starter
    1.68
    ())
    1.60
     thereof
    1.51
    Pub
    1.50
    ('',
    1.45
    prototype
    1.43
    CDATA
    1.40
     remedies
    1.40
    /)
    1.39
    heets
    1.37
    Activations Density 0.282%

    No Known Activations