Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26283
    Prev
    Next
    INDEX
    Explanations

    numerical values related to statistics or measurements 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
    42
    +0.13
    0.7%
    497
    +0.12
    0.7%
    159
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.13
    0.05
    82
    +0.12
    0.03
    497
    +0.11
    0.01
    Negative Logits
    Ń
    -1.93
    º
    -1.77
    ½
    -1.77
    Į
    -1.68
    Ŀ
    -1.65
    ®
    -1.59
    ¹
    -1.57
     Merkel
    -1.56
    fully
    -1.54
    izes
    -1.54
    POSITIVE LOGITS
    ITED
    1.62
    APTER
    1.49
     dB
    1.49
    atha
    1.42
    idd
    1.41
    oint
    1.38
     Chap
    1.36
    ATH
    1.36
     innings
    1.35
     chan
    1.32
    Activations Density 0.275%

    No Known Activations