© 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. 2-MLP-SM
    11. 23688
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and expressions

    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
    360
    +0.14
    0.7%
    271
    +0.13
    0.7%
    28
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    360
    +0.14
    0.02
    414
    +0.13
    0.01
    45
    +0.12
    0.02
    Negative Logits
    achine
    -1.51
    ureus
    -1.42
    bane
    -1.42
    ]{.
    -1.39
    acter
    -1.39
    ]\\
    -1.38
    bee
    -1.35
     honored
    -1.32
     grounded
    -1.31
    atum
    -1.30
    POSITIVE LOGITS
    ¡
    2.87
    »¿
    2.84
    £
    2.61
    Ļª
    2.54
    ¶
    2.49
    Ģ
    2.49
    «
    2.40
    ®
    2.34
    ·¸
    2.22
    ĸ´
    2.20
    Activations Density 0.044%

    No Known Activations