© 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 EvalsExportsAPI 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. 28734
    Prev
    Next
    INDEX
    Explanations

    terms related to adsorption processes

    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
    156
    +0.26
    1.6%
    320
    +0.12
    0.7%
    46
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    320
    +0.26
    0.01
    102
    +0.12
    0.01
    156
    +0.11
    0.01
    Negative Logits
    ĥ½
    -1.70
    "_
    -1.60
    }|^
    -1.58
    rely
    -1.54
    ¸
    -1.51
    asts
    -1.49
    respond
    -1.46
    aq
    -1.42
     traveled
    -1.42
    edes
    -1.41
    POSITIVE LOGITS
    ist
    1.82
    pective
    1.68
    hoc
    1.63
    ariate
    1.61
    naire
    1.61
    istine
    1.60
    able
    1.53
    ilent
    1.52
    istan
    1.45
     era
    1.40
    Activations Density 0.009%

    No Known Activations