© 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 EvalsExportsinterp-engineNEWAPI 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. 22852
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "as" in various 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
    97
    +0.15
    0.9%
    123
    +0.14
    0.8%
    36
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    97
    +0.15
    0.02
    402
    +0.14
    0.02
    123
    +0.13
    0.02
    Negative Logits
    hler
    -1.58
     drunken
    -1.49
    vere
    -1.48
     crashes
    -1.44
    wey
    -1.43
    rika
    -1.41
    illery
    -1.40
    arten
    -1.39
    arson
    -1.39
     2003
    -1.39
    POSITIVE LOGITS
    InstanceState
    2.04
    !(
    1.68
    ä¹Ī
    1.60
    noreply
    1.60
    +/
    1.51
    Inflater
    1.49
    ubottu
    1.48
    rive
    1.48
    *}
    1.48
    cif
    1.45
    Activations Density 0.129%

    No Known Activations