© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27009
    Prev
    Next
    INDEX
    Explanations

    phrases expressing the concept of possibility or potential

    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
    439
    +0.13
    0.7%
    177
    +0.13
    0.7%
    152
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    423
    +0.13
    0.06
    454
    +0.13
    0.03
    142
    +0.12
    0.05
    Negative Logits
    *(
    -1.60
    ered
    -1.58
     background
    -1.56
    ork
    -1.45
    att
    -1.41
    pping
    -1.41
     backgrounds
    -1.38
    idd
    -1.37
    lain
    -1.36
     DH
    -1.32
    POSITIVE LOGITS
    ĨĴ
    2.38
    Į
    2.38
    ½
    2.34
    ĥ½
    2.31
    ¬
    2.19
    »¿
    2.16
    «
    2.15
    Ń
    2.15
    Ħ
    2.10
    º
    2.09
    Activations Density 0.340%

    No Known Activations