© 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. 24790
    Prev
    Next
    INDEX
    Explanations

    terms related to breadth or general scope

    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
    449
    +0.17
    1.0%
    378
    +0.16
    0.9%
    285
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    277
    +0.17
    0.08
    285
    +0.16
    0.07
    23
    +0.12
    0.03
    Negative Logits
    those
    -1.66
    glich
    -1.61
    aines
    -1.57
    blogger
    -1.50
    .”
    -1.47
    ĨĴ
    -1.46
    these
    -1.42
    º
    -1.39
    ains
    -1.39
    unners
    -1.37
    POSITIVE LOGITS
     priority
    1.50
     theor
    1.32
     riots
    1.31
     instit
    1.31
    ma
    1.28
    ori
    1.28
    orie
    1.28
    ORDER
    1.28
    DEC
    1.23
     Mao
    1.22
    Activations Density 1.072%

    No Known Activations