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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 23066
    Prev
    Next
    INDEX
    Explanations

    key characters and their actions in a narrative

    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
    156
    +0.23
    1.3%
    338
    +0.15
    0.8%
    59
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    338
    +0.23
    0.03
    444
    +0.15
    0.01
    82
    +0.14
    0.02
    Negative Logits
     pronounced
    -1.39
     advantage
    -1.31
    agents
    -1.31
    abouts
    -1.28
     consequent
    -1.26
    station
    -1.24
    decoration
    -1.24
    agent
    -1.23
    fare
    -1.22
    '):
    -1.21
    POSITIVE LOGITS
    ¿
    4.47
    Ļª
    4.34
    ĻĤ
    4.30
    §
    4.16
    ¥
    4.13
    ³
    4.13
    ¦
    4.13
    į
    4.08
    ģ
    4.03
    ½
    3.96
    Activations Density 3.486%

    No Known Activations