© 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. 22763
    Prev
    Next
    INDEX
    Explanations

    references to African American representation and issues

    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
    23
    +0.22
    1.2%
    429
    +0.15
    0.8%
    333
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.22
    0.07
    125
    +0.15
    0.10
    79
    +0.12
    0.09
    Negative Logits
    iary
    -1.75
    caster
    -1.75
    ’
    -1.65
    dimen
    -1.58
    door
    -1.54
    lected
    -1.54
     dimension
    -1.52
    ÃŃa
    -1.51
     pode
    -1.49
     (“
    -1.46
    POSITIVE LOGITS
    ¿½
    1.83
    Īĺ
    1.83
    ĻĤ
    1.81
    «
    1.77
    ħ
    1.76
    ·¸
    1.75
    ¦
    1.73
    ĵ
    1.70
    Ļ
    1.69
    ³
    1.67
    Activations Density 2.319%

    No Known Activations