© 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. 0-MLP-SM
    6. 27717
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly highlighting significant statistics or data points

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    458
    +0.16
    0.9%
    362
    +0.13
    0.7%
    81
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    199
    +0.16
    0.04
    12
    +0.13
    0.03
    458
    +0.13
    0.03
    Negative Logits
    ĨĴ
    -1.75
    »¿
    -1.70
    ¿½
    -1.64
    uppose
    -1.61
     pity
    -1.58
    Ĥ¬
    -1.54
    ĸ´
    -1.51
     rodents
    -1.45
    rept
    -1.45
    ats
    -1.44
    POSITIVE LOGITS
     states
    1.50
     dressing
    1.44
     senses
    1.41
     (,
    1.41
    ermost
    1.34
    dock
    1.34
    enson
    1.34
    inski
    1.33
    sky
    1.33
    mann
    1.33
    Activations Density 1.474%

    No Known Activations