© 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. 2-MLP-SM
    11. 23218
    Prev
    Next
    INDEX
    Explanations

    the presence or context of the word "at" in various forms and frequencies throughout 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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    310
    +0.14
    0.8%
    195
    +0.12
    0.7%
    170
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.14
    0.06
    33
    +0.12
    0.05
    442
    +0.11
    0.04
    Negative Logits
     uniform
    -1.66
     face
    -1.50
     tack
    -1.40
     stranger
    -1.40
     calm
    -1.31
    iator
    -1.29
    ities
    -1.26
    sense
    -1.26
     view
    -1.25
     extrinsic
    -1.25
    POSITIVE LOGITS
    ĥ½
    2.86
    ↵↵
    2.47
     ↵
    2.47
    ↵
    2.47
    č↵
    2.47
             ↵
    2.47
    ↵
    2.47
    č↵
    2.47
    <|outofrange|>
    2.47
    ↵
    2.47
    Activations Density 0.352%

    No Known Activations