© 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. 29726
    Prev
    Next
    INDEX
    Explanations

    instances of the word "roughly."

    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
    +0.19
    1.1%
    156
    +0.15
    0.9%
    86
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.19
    0.02
    86
    +0.15
    0.02
    69
    +0.13
    0.02
    Negative Logits
    nd
    -1.73
    ello
    -1.65
    ele
    -1.64
    ove
    -1.64
    PM
    -1.57
    APDH
    -1.56
    PE
    -1.56
    LF
    -1.54
    arb
    -1.54
    arshal
    -1.49
    POSITIVE LOGITS
     dated
    1.69
     ?>
    1.57
    ¡
    1.55
    ?:
    1.49
    ¿½
    1.44
    ?'
    1.42
    ?>
    1.40
    coming
    1.40
    µ
    1.38
    chaft
    1.36
    Activations Density 2.123%

    No Known Activations