© 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. 29856
    Prev
    Next
    INDEX
    Explanations

    references to tin or related discussions 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
    243
    +0.17
    1.0%
    489
    +0.15
    0.9%
    456
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    243
    +0.17
    0.01
    489
    +0.15
    0.01
    162
    +0.11
    0.01
    Negative Logits
     _
    -1.88
     slightest
    -1.87
     someone
    -1.69
     somebody
    -1.67
     neut
    -1.65
     float
    -1.63
     me
    -1.62
     convergence
    -1.59
     drift
    -1.56
     [*
    -1.55
    POSITIVE LOGITS
    cript
    1.92
    works
    1.82
    etts
    1.76
    holm
    1.75
    istry
    1.75
    hurst
    1.70
    erals
    1.68
    hearted
    1.66
    bourne
    1.66
    door
    1.66
    Activations Density 0.014%

    No Known Activations