© 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. 25270
    Prev
    Next
    INDEX
    Explanations

    code structure elements such as function definitions and syntax operators

    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
    24
    +0.14
    0.8%
    188
    +0.13
    0.7%
    451
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.14
    0.02
    24
    +0.13
    0.03
    94
    +0.12
    0.03
    Negative Logits
    orms
    -1.68
    smallcaps
    -1.68
     anaest
    -1.63
    oretic
    -1.51
    chaft
    -1.50
     =&
    -1.49
    propto
    -1.49
    asy
    -1.41
     .\
    -1.39
    ollen
    -1.38
    POSITIVE LOGITS
    standing
    1.47
    ality
    1.44
     beauty
    1.37
     logo
    1.37
    belt
    1.36
    ENTIAL
    1.33
     drafted
    1.33
     aspects
    1.33
    binding
    1.33
     framed
    1.31
    Activations Density 0.117%

    No Known Activations