© 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. 30342
    Prev
    Next
    INDEX
    Explanations

    instances of the word "figured."

    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
    +0.25
    1.4%
    115
    +0.15
    0.9%
    95
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    94
    +0.25
    0.01
    95
    +0.15
    0.01
    437
    +0.13
    0.01
    Negative Logits
    pired
    -1.60
    scribed
    -1.56
    Decided
    -1.51
    ENTS
    -1.42
    IAN
    -1.42
     grade
    -1.41
     variance
    -1.39
    elf
    -1.38
    ism
    -1.38
    ES
    -1.37
    POSITIVE LOGITS
    ķ
    1.98
    ĻĤ
    1.84
     prominently
    1.74
    ¿½
    1.64
    Ķ
    1.62
    ilit
    1.61
    ¤
    1.59
    1.59
    <|outofrange|>
    1.59
    č↵
    1.59
    Activations Density 0.014%

    No Known Activations