© 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. 2-MLP-SM
    11. 22764
    Prev
    Next
    INDEX
    Explanations

    assertions of necessity or need 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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    463
    +0.14
    0.8%
    114
    +0.11
    0.6%
    140
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    463
    +0.14
    0.15
    364
    +0.11
    0.16
    399
    +0.10
    0.13
    Negative Logits
    omorphic
    -1.58
    '))
    -1.51
    .[]{
    -1.43
    inous
    -1.41
    ocarcin
    -1.36
    reements
    -1.36
    esides
    -1.31
    while
    -1.30
    thon
    -1.30
    formed
    -1.29
    POSITIVE LOGITS
    ¦
    1.93
    İ
    1.86
    Ĭ
    1.84
    ļ
    1.81
    ³
    1.78
    ¿½
    1.77
    ij
    1.75
    ħ
    1.66
    ł
    1.65
    °
    1.64
    Activations Density 1.727%

    No Known Activations