© 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. 26028
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to evidence and attachment

    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
    193
    +0.13
    0.7%
    309
    +0.12
    0.7%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.13
    0.06
    53
    +0.12
    0.07
    56
    +0.12
    0.01
    Negative Logits
    ĥ½
    -2.40
    ij
    -2.39
    º
    -2.17
    ľĵ
    -2.10
    Ĵ
    -2.06
    ´
    -2.05
    Ĥ¬
    -1.92
    ·
    -1.91
    ĵ
    -1.90
    Ħ
    -1.86
    POSITIVE LOGITS
    forest
    1.59
    athi
    1.58
    NAL
    1.55
    ppo
    1.47
    ford
    1.45
    plicate
    1.45
    onet
    1.42
    blr
    1.39
    pler
    1.37
    ellen
    1.37
    Activations Density 4.641%

    No Known Activations