© 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. 28006
    Prev
    Next
    INDEX
    Explanations

    references to "spin" or related terms

    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
    376
    +0.11
    0.6%
    336
    +0.10
    0.6%
    59
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.11
    0.01
    336
    +0.10
    0.01
    319
    +0.10
    0.01
    Negative Logits
    »
    -2.61
    ĥ
    -2.36
    ¿
    -2.33
    ļ
    -2.33
    Ŀ
    -2.30
    į
    -2.21
    ĸ´
    -2.21
    »¿
    -2.15
    İ
    -2.12
    ĵ
    -2.09
    POSITIVE LOGITS
    burg
    1.75
    oon
    1.68
    berg
    1.63
    ozo
    1.55
    below
    1.54
    RH
    1.49
    boat
    1.47
    opian
    1.46
    upt
    1.43
    othal
    1.42
    Activations Density 0.118%

    No Known Activations