© 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. 25502
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaboration and community support in the arts

    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
    23
    +0.45
    3.3%
    203
    +0.21
    1.5%
    478
    +0.20
    1.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.45
    0.35
    23
    +0.21
    0.32
    494
    +0.20
    0.26
    Negative Logits
    ĻĤ
    -2.39
    ,
    -2.18
    -âĤ¬
    -2.09
    :`
    -1.94
    wagen
    -1.89
    ista
    -1.86
     ("
    -1.85
    !,
    -1.83
    ,[
    -1.81
    estock
    -1.79
    POSITIVE LOGITS
    respectively
    1.91
    omitempty
    1.83
    signed
    1.79
     therefore
    1.71
    ``
    1.70
    ÑĢоÑģ
    1.69
    thus
    1.65
    which
    1.65
    000
    1.64
    otherwise
    1.63
    Activations Density 10.962%

    No Known Activations