© 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. 26412
    Prev
    Next
    INDEX
    Explanations

    the term 'TER' in various contexts

    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
    469
    +0.12
    0.7%
    111
    +0.11
    0.7%
    77
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.12
    0.02
    385
    +0.11
    0.02
    78
    +0.11
    0.01
    Negative Logits
    hern
    -1.90
     others
    -1.68
    compan
    -1.51
    itter
    -1.48
    others
    -1.48
    tern
    -1.45
    ursed
    -1.45
     fatal
    -1.38
     done
    -1.37
    hem
    -1.36
    POSITIVE LOGITS
    oku
    1.73
    osse
    1.65
    umab
    1.60
    itect
    1.59
    nas
    1.51
    prises
    1.50
    nae
    1.49
     Estate
    1.47
    bellum
    1.46
    pha
    1.45
    Activations Density 0.018%

    No Known Activations