© 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. 27190
    Prev
    Next
    INDEX
    Explanations

    the presence of copyright or licensing information

    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
    43
    +0.13
    0.7%
    54
    +0.12
    0.7%
    242
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.13
    0.24
    486
    +0.12
    0.16
    154
    +0.11
    0.15
    Negative Logits
     sometimes
    -1.71
     occasionally
    -1.54
    iates
    -1.52
     FIGS
    -1.44
     FIG
    -1.42
    sometimes
    -1.37
     dances
    -1.35
     various
    -1.35
    FIG
    -1.34
     extensively
    -1.34
    POSITIVE LOGITS
    ľĵ
    2.11
    Ĺ
    2.03
    ī
    1.85
    Ĩ
    1.79
    ¹
    1.78
    ĨĴ
    1.77
    Ī
    1.75
    ĸ
    1.75
    fileID
    1.75
    Ŀ
    1.67
    Activations Density 0.347%

    No Known Activations