© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27006
    Prev
    Next
    INDEX
    Explanations

    terms related to subjective and objective assessments

    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
    156
    +0.16
    0.9%
    46
    +0.14
    0.8%
    266
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.16
    0.01
    46
    +0.14
    0.01
    102
    +0.13
    0.01
    Negative Logits
    ]>
    -1.56
    sel
    -1.54
    ht
    -1.53
    her
    -1.49
    aned
    -1.48
    rap
    -1.47
     hers
    -1.46
    acetic
    -1.42
    ushed
    -1.39
    ower
    -1.39
    POSITIVE LOGITS
    Īĺ
    2.16
    ´
    2.10
    µ
    2.08
    ¢
    2.03
    º
    1.98
    ¾
    1.95
    ¡
    1.95
    ®
    1.92
    ¼
    1.90
    ļ
    1.88
    Activations Density 0.018%

    No Known Activations