© 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. 25286
    Prev
    Next
    INDEX
    Explanations

    instances 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
    387
    +0.13
    0.7%
    407
    +0.12
    0.7%
    160
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.13
    0.14
    394
    +0.12
    0.14
    407
    +0.11
    0.14
    Negative Logits
    ¿½
    -2.97
    ľ
    -2.32
    ©
    -2.25
    ·¸
    -2.17
    ¹
    -1.99
    Īĺ
    -1.95
    ¶
    -1.94
    ł
    -1.91
    ·
    -1.90
    °
    -1.88
    POSITIVE LOGITS
    acter
    1.69
    /-/
    1.66
    úblic
    1.63
     pyl
    1.58
    ressor
    1.55
    osse
    1.54
    #:
    1.52
    apes
    1.51
    bibr
    1.50
    Pub
    1.50
    Activations Density 1.524%

    No Known Activations