© 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. 24872
    Prev
    Next
    INDEX
    Explanations

    information related to measurements and numerical data in scientific 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
    156
    +0.19
    1.1%
    230
    +0.13
    0.7%
    168
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    230
    +0.19
    0.01
    30
    +0.13
    0.02
    92
    +0.12
    0.02
    Negative Logits
    ties
    -1.79
    ty
    -1.59
     ±
    -1.45
    stroke
    -1.40
    faced
    -1.37
    liest
    -1.36
    cano
    -1.32
    otta
    -1.30
    stage
    -1.30
    bbe
    -1.29
    POSITIVE LOGITS
     Nothing
    1.39
    iment
    1.38
     Marriage
    1.33
     Atty
    1.33
     COPYRIGHT
    1.31
    EMENT
    1.31
    iah
    1.27
    endra
    1.26
     Return
    1.25
     Rights
    1.23
    Activations Density 0.168%

    No Known Activations