© 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. 2-MLP-SM
    11. 24659
    Prev
    Next
    INDEX
    Explanations

    phrases relating to conditions and characteristics, particularly those involving "to be" and related constructions

    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
    431
    +0.13
    0.7%
    27
    +0.13
    0.7%
    333
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    368
    +0.13
    0.02
    77
    +0.13
    0.02
    27
    +0.12
    0.01
    Negative Logits
    »¿
    -1.92
    til
    -1.84
    ridges
    -1.66
    «
    -1.63
    Ĥ
    -1.61
    £
    -1.61
    ede
    -1.59
    edes
    -1.56
    annotations
    -1.54
    rig
    -1.52
    POSITIVE LOGITS
    ATOR
    1.59
    ARY
    1.55
    ums
    1.44
    ?
    1.41
    iah
    1.41
     hours
    1.41
    ateness
    1.38
     clinic
    1.37
    amazon
    1.36
    IER
    1.36
    Activations Density 0.158%

    No Known Activations