© 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. 25337
    Prev
    Next
    INDEX
    Explanations

    references to the English language and its variations

    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
    65
    +0.12
    0.7%
    349
    +0.11
    0.6%
    76
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.12
    0.01
    65
    +0.11
    0.01
    349
    +0.10
    0.01
    Negative Logits
    ¬
    -2.98
    ³
    -2.75
    ´
    -2.73
    ¶
    -2.64
    ĥ½
    -2.64
    Ĭ
    -2.53
    Ī
    -2.52
    Ħ
    -2.43
    ī
    -2.42
    µ
    -2.39
    POSITIVE LOGITS
    amer
    1.83
    dbg
    1.76
    books
    1.73
    Unmarshal
    1.72
    amers
    1.70
    watson
    1.66
    heets
    1.65
    bench
    1.64
    FW
    1.64
    cias
    1.63
    Activations Density 0.024%

    No Known Activations