© 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. 23678
    Prev
    Next
    INDEX
    Explanations

    phrases related to features and attributes of films or events

    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
    156
    +0.32
    1.8%
    174
    +0.14
    0.8%
    20
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.32
    0.07
    85
    +0.14
    0.04
    20
    +0.14
    0.09
    Negative Logits
     funnel
    -1.59
    ishly
    -1.44
    úblic
    -1.40
     echo
    -1.36
     obstacle
    -1.33
     dream
    -1.33
     pleased
    -1.29
     gratefully
    -1.24
     merge
    -1.24
     thrilled
    -1.24
    POSITIVE LOGITS
    ĭ
    1.69
    ±
    1.66
    »
    1.65
    lu
    1.62
    ³
    1.52
    Ĥ
    1.51
    ings
    1.47
    ·¸
    1.43
    ¦
    1.42
    rå
    1.40
    Activations Density 1.530%

    No Known Activations