© 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. 0-MLP-SM
    11. 25753
    Prev
    Next
    INDEX
    Explanations

    the term "existing" in various contexts related to concepts of permanence or presence

    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
    380
    +0.13
    0.7%
    156
    +0.12
    0.7%
    40
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    40
    +0.13
    0.01
    121
    +0.12
    0.01
    460
    +0.11
    0.01
    Negative Logits
    ĥ½
    -1.89
    ľ
    -1.87
    ī
    -1.67
     pronounced
    -1.61
     dawn
    -1.60
    Ī
    -1.56
    ĥ
    -1.55
    ¿½
    -1.53
    ĺ
    -1.51
     me
    -1.50
    POSITIVE LOGITS
    eca
    2.06
    caster
    1.89
    ism
    1.87
    mind
    1.78
    fors
    1.76
    endor
    1.70
    8859
    1.67
    verter
    1.65
    lane
    1.64
    isms
    1.63
    Activations Density 0.015%

    No Known Activations