© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 28791
    Prev
    Next
    INDEX
    Explanations

    terms related to reconstruction and corruption

    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
    115
    +0.16
    0.9%
    334
    +0.15
    0.8%
    507
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.16
    0.02
    507
    +0.15
    0.03
    115
    +0.12
    0.03
    Negative Logits
    forth
    -1.59
    ctor
    -1.57
    zc
    -1.53
    fun
    -1.48
    ction
    -1.46
    cz
    -1.44
    floor
    -1.44
    quo
    -1.44
     Register
    -1.42
    zen
    -1.41
    POSITIVE LOGITS
    ing
    3.36
    s
    3.00
    Ģ
    2.62
    ij
    2.55
    Ļª
    2.52
    İ
    2.45
    ©
    2.44
    Ŀ
    2.38
    ŀ
    2.38
    ½
    2.36
    Activations Density 0.091%

    No Known Activations