© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26422
    Prev
    Next
    INDEX
    Explanations

    terms related to real-time processing and monitoring solutions

    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
    469
    +0.12
    0.7%
    405
    +0.12
    0.7%
    222
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    462
    +0.12
    0.01
    289
    +0.12
    0.03
    405
    +0.11
    0.02
    Negative Logits
    ary
    -2.25
    aries
    -2.19
    esian
    -1.90
    nier
    -1.76
    ARY
    -1.75
    iors
    -1.71
    pires
    -1.61
    jah
    -1.60
    ward
    -1.59
    avian
    -1.59
    POSITIVE LOGITS
    ":["
    1.41
    °
    1.41
     Lic
    1.31
    '=>
    1.28
    ','
    1.27
    ':'
    1.26
     }_{
    1.25
    '},
    1.22
     deletions
    1.21
    Ĥ
    1.21
    Activations Density 0.350%

    No Known Activations