© 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. 27673
    Prev
    Next
    INDEX
    Explanations

    references to political figures, specifically the president

    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
    +0.17
    1.0%
    376
    +0.12
    0.7%
    365
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    133
    +0.17
    0.03
    202
    +0.12
    0.03
    365
    +0.12
    0.02
    Negative Logits
    ĥ½
    -2.42
    ŀ
    -1.80
    Ĥ
    -1.74
    ¢
    -1.72
    ĵ
    -1.69
    ij
    -1.69
    ¬
    -1.68
    backs
    -1.66
     Respondents
    -1.60
    Ĵ
    -1.60
    POSITIVE LOGITS
    doms
    1.92
    coat
    1.91
    zilla
    1.74
    brush
    1.71
    sheet
    1.70
    liness
    1.65
    esses
    1.63
    ee
    1.59
    urally
    1.59
    们
    1.58
    Activations Density 0.021%

    No Known Activations