© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 28210
    Prev
    Next
    INDEX
    Explanations

    mentions of software dependencies

    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
    376
    +0.19
    1.1%
    156
    +0.17
    1.0%
    29
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    40
    +0.19
    0.01
    149
    +0.17
    0.01
    29
    +0.13
    0.01
    Negative Logits
    ureus
    -1.65
    ateurs
    -1.55
    edes
    -1.52
    uen
    -1.52
    yd
    -1.49
    Ĵ
    -1.44
     something
    -1.44
     mere
    -1.42
     moonlight
    -1.39
    ussi
    -1.38
    POSITIVE LOGITS
    ÅĽci
    1.97
     era
    1.65
     crop
    1.59
    etting
    1.58
    hell
    1.56
    ÅĽÄĩ
    1.54
    grass
    1.53
    ructions
    1.53
    pile
    1.51
    umber
    1.47
    Activations Density 0.009%

    No Known Activations