© 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. 25474
    Prev
    Next
    INDEX
    Explanations

    the word "biz" and its variations occurring frequently in the text

    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
    +0.12
    0.7%
    286
    +0.12
    0.7%
    260
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    286
    +0.12
    0.02
    313
    +0.12
    0.02
    475
    +0.10
    0.02
    Negative Logits
    ´
    -2.82
    Īĺ
    -2.45
    µ
    -2.30
    Ĥ
    -2.28
    Ħ
    -2.03
    Ĭ
    -1.99
    Ī
    -1.91
    ¦
    -1.89
    yline
    -1.88
    ¶
    -1.86
    POSITIVE LOGITS
     authorities
    1.84
     pend
    1.58
    utory
    1.56
     factors
    1.53
     device
    1.51
     locks
    1.49
     inflation
    1.47
     precedent
    1.47
     risks
    1.45
    bon
    1.42
    Activations Density 0.017%

    No Known Activations