© 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. 28243
    Prev
    Next
    INDEX
    Explanations

    references to bats

    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
    376
    +0.15
    0.8%
    148
    +0.11
    0.6%
    481
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.15
    0.01
    108
    +0.11
    0.01
    76
    +0.11
    0.01
    Negative Logits
    Ĥ¬
    -3.26
    ĭ
    -3.17
    »¿
    -3.13
    ·¸
    -3.11
    Ń
    -3.07
    ľ
    -3.06
    µ
    -3.06
    ĥ½
    -2.90
    ĺ
    -2.82
    ¿½
    -2.81
    POSITIVE LOGITS
    kat
    1.75
    etto
    1.68
    ouch
    1.67
    shock
    1.61
    ikt
    1.56
    etts
    1.55
    ienn
    1.53
    ious
    1.53
    ppo
    1.52
    enance
    1.50
    Activations Density 0.009%

    No Known Activations