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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27701
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of utilization or usage

    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
    +0.28
    1.6%
    376
    +0.19
    1.1%
    69
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.28
    0.02
    12
    +0.19
    0.01
    373
    +0.11
    0.01
    Negative Logits
    owski
    -1.69
    HEP
    -1.62
    MOESM
    -1.57
    brahim
    -1.51
     Publ
    -1.45
    supplementary
    -1.45
    GN
    -1.44
    unnumbered
    -1.42
    âĺħ
    -1.39
    ì§
    -1.38
    POSITIVE LOGITS
    ľĵ
    2.33
    ł
    2.22
    ©
    2.16
     contradiction
    2.01
    °
    2.00
    Ļ
    1.95
    ¨
    1.88
    Ĺ
    1.79
    Ķ
    1.73
    ĺ
    1.72
    Activations Density 0.730%

    No Known Activations