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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 26512
    Prev
    Next
    INDEX
    Explanations

    terms related to experimental responses and measurements in scientific studies

    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
    263
    +0.13
    0.7%
    169
    +0.13
    0.7%
    172
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    120
    +0.13
    0.08
    208
    +0.13
    0.05
    168
    +0.12
    0.06
    Negative Logits
    olves
    -1.81
    soever
    -1.80
    versus
    -1.51
    ples
    -1.50
    hou
    -1.40
    yrs
    -1.38
    ensively
    -1.37
    ensitive
    -1.33
    hua
    -1.33
     note
    -1.33
    POSITIVE LOGITS
    Ń
    2.05
    ĵ
    1.88
    ½
    1.84
    ¬
    1.75
    «
    1.74
    ³
    1.70
    İ
    1.64
    »
    1.58
    ¶
    1.56
    ¹
    1.56
    Activations Density 0.646%

    No Known Activations