© 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. 25995
    Prev
    Next
    INDEX
    Explanations

    documentation and license-related references

    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
    23
    +0.14
    0.8%
    424
    +0.12
    0.7%
    361
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.14
    0.04
    386
    +0.12
    0.01
    474
    +0.12
    0.02
    Negative Logits
    googleapis
    -1.82
    cript
    -1.70
    doibase
    -1.69
    wort
    -1.68
    iterr
    -1.66
    argv
    -1.64
    izumab
    -1.64
    icile
    -1.54
     forum
    -1.53
     forums
    -1.46
    POSITIVE LOGITS
    ĸ
    3.17
    IJ
    3.15
    ¨
    3.08
    ĩ
    3.08
    ´
    3.02
    ¼
    2.98
    ²
    2.89
    ¯
    2.83
    ķ
    2.79
    Ĭ
    2.79
    Activations Density 0.157%

    No Known Activations