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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28227
    Prev
    Next
    INDEX
    Explanations

    references to processes or functions

    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
    111
    +0.18
    1.0%
    410
    +0.16
    0.9%
    444
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.18
    0.02
    360
    +0.16
    0.02
    444
    +0.13
    0.02
    Negative Logits
    giene
    -1.53
    isation
    -1.52
    ontrol
    -1.39
    argin
    -1.39
     respectively
    -1.37
    illance
    -1.36
    mente
    -1.35
    tern
    -1.34
    "?
    -1.34
    ising
    -1.32
    POSITIVE LOGITS
    «
    3.65
    ·
    3.55
    ĺ
    3.39
    ľ
    3.19
    ŀ
    3.17
    Ĵ
    3.16
    ģ
    3.14
    Ŀ
    3.12
    ©
    3.06
    ¢
    2.97
    Activations Density 0.011%

    No Known Activations