© 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. 23254
    Prev
    Next
    INDEX
    Explanations

    instances of specific names and terms related to people and places

    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
    79
    +0.13
    0.7%
    243
    +0.12
    0.7%
    463
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    463
    +0.13
    0.06
    79
    +0.12
    0.09
    254
    +0.12
    0.03
    Negative Logits
     contradiction
    -1.51
    OSE
    -1.48
     pretext
    -1.46
    comparison
    -1.42
     APPEALS
    -1.41
     edema
    -1.35
    absorption
    -1.31
    cancers
    -1.29
     whites
    -1.27
    OutputStream
    -1.26
    POSITIVE LOGITS
    Ĵ
    2.23
    »
    2.15
    ¼
    2.14
    ĻĤ
    1.98
    »¿
    1.86
    ħ
    1.85
    ·¸
    1.81
     [âĢ¦]
    1.80
    ģ
    1.75
    Ĭ
    1.68
    Activations Density 1.862%

    No Known Activations