© 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. 22888
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to computational processes and resources

    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
    289
    +0.16
    0.9%
    167
    +0.13
    0.7%
    278
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.16
    0.12
    278
    +0.13
    0.03
    57
    +0.12
    0.07
    Negative Logits
    dev
    -1.61
    inte
    -1.61
    continue
    -1.57
    ttp
    -1.50
     profitable
    -1.47
    raise
    -1.47
    thems
    -1.46
    ribute
    -1.45
    ...](
    -1.44
    API
    -1.43
    POSITIVE LOGITS
    ĻĤ
    3.33
    «
    3.18
    ij
    3.12
    IJ
    3.08
    ¥
    3.00
    Īĺ
    2.98
    ¸
    2.93
    ±
    2.92
    Ľ
    2.89
    ¿½
    2.87
    Activations Density 3.726%

    No Known Activations