© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 25754
    Prev
    Next
    INDEX
    Explanations

    mentions of incidents or claims related to protests or demands for rights

    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
    123
    +0.16
    0.9%
    33
    +0.11
    0.6%
    392
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.16
    0.10
    108
    +0.11
    0.13
    407
    +0.11
    0.13
    Negative Logits
     minute
    -1.77
     instant
    -1.72
    atus
    -1.64
    unction
    -1.56
    ť
    -1.52
    ://
    -1.48
     curvature
    -1.46
    iative
    -1.45
    headed
    -1.38
    ered
    -1.35
    POSITIVE LOGITS
    IJ
    2.67
    ĸ
    2.56
    ĥ½
    2.50
    ·
    2.25
    º
    2.24
    ½
    2.22
    Į
    2.13
    Ĥ
    2.12
    Ĭ
    2.12
    ¢
    2.08
    Activations Density 2.412%

    No Known Activations