© 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. 30283
    Prev
    Next
    INDEX
    Explanations

    instances of the word "bin"

    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
    454
    +0.12
    0.7%
    139
    +0.12
    0.7%
    465
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    465
    +0.12
    0.03
    454
    +0.12
    0.02
    363
    +0.12
    0.02
    Negative Logits
    ]>
    -1.70
     #{
    -1.66
     MERCHANTABILITY
    -1.60
    ]=
    -1.44
    *=
    -1.43
     myself
    -1.38
     brow
    -1.37
     *.
    -1.32
     slightest
    -1.32
    aning
    -1.31
    POSITIVE LOGITS
    ĻĤ
    1.94
    ®
    1.93
    ¿½
    1.89
    shots
    1.87
    Ŀ
    1.86
    ¬
    1.78
     shots
    1.75
    aret
    1.73
    iere
    1.73
    ª
    1.70
    Activations Density 0.022%

    No Known Activations