© 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. 25962
    Prev
    Next
    INDEX
    Explanations

    words that indicate success or achievement

    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
    156
    +0.31
    1.8%
    376
    +0.14
    0.9%
    487
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    487
    +0.31
    0.03
    266
    +0.14
    0.03
    156
    +0.12
    0.02
    Negative Logits
    rox
    -1.75
    urane
    -1.59
    liche
    -1.46
    ξ
    -1.43
    ene
    -1.42
    urg
    -1.41
    aned
    -1.36
    RB
    -1.33
    η
    -1.33
    ISH
    -1.31
    POSITIVE LOGITS
    Īĺ
    2.81
    ł
    2.49
    ¸
    2.42
    ĻĤ
    2.38
    Ĥ¬
    2.29
    ¼
    2.21
    ²
    2.18
    Ģ
    2.06
    ķ
    2.06
    Ł
    2.02
    Activations Density 0.049%

    No Known Activations