© 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 EvalsExportsAPI 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. 29028
    Prev
    Next
    INDEX
    Explanations

    references to outsiders or external groups

    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
    52
    +0.11
    0.7%
    376
    +0.11
    0.6%
    456
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    24
    +0.11
    0.01
    52
    +0.11
    0.01
    76
    +0.10
    0.01
    Negative Logits
    rians
    -2.04
    rian
    -1.93
    resses
    -1.77
    ?’
    -1.76
     rash
    -1.53
    ushed
    -1.52
     '</
    -1.50
     slightest
    -1.50
     somebody
    -1.47
     kind
    -1.45
    POSITIVE LOGITS
    µ
    3.13
    Ŀ
    2.86
    ¡
    2.80
    ½
    2.80
    ¿
    2.74
    ļ
    2.73
    ĭ
    2.68
    ®
    2.68
    2.67
    ¸
    2.67
    Activations Density 0.016%

    No Known Activations