© 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. 30655
    Prev
    Next
    INDEX
    Explanations

    opening and closing braces in code

    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
    478
    +0.18
    1.0%
    414
    +0.12
    0.7%
    176
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    175
    +0.18
    0.08
    414
    +0.12
    0.07
    145
    +0.12
    0.07
    Negative Logits
    osal
    -1.55
    /%
    -1.51
    ary
    -1.47
    uit
    -1.46
    ical
    -1.45
    omorphic
    -1.41
    ](
    -1.41
    ilibrium
    -1.38
    itation
    -1.37
    ations
    -1.37
    POSITIVE LOGITS
    ĨĴ
    2.03
    ¡
    1.99
    mathrsfs
    1.92
    ķ
    1.91
    amsbsy
    1.85
    ¥
    1.84
    ĸ
    1.83
    amsfonts
    1.67
    amssymb
    1.58
    wasysym
    1.58
    Activations Density 0.309%

    No Known Activations