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

    Neuronpedia

    Jacobian LensNEW
    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. 29401
    Prev
    Next
    INDEX
    Explanations

    the pronoun "it."

    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
    413
    +0.16
    0.9%
    95
    +0.15
    0.8%
    473
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.16
    0.22
    185
    +0.15
    0.18
    165
    +0.12
    0.17
    Negative Logits
    uximab
    -1.99
    »
    -1.93
    Ħ
    -1.93
    ¼
    -1.91
    ī
    -1.90
    ľĵ
    -1.84
    ¿½
    -1.83
    Ĥ
    -1.82
    ½
    -1.81
    ĺ
    -1.71
    POSITIVE LOGITS
    except
    1.75
    ly
    1.52
    arning
    1.51
     except
    1.47
    antly
    1.45
    mente
    1.42
     sight
    1.41
    ights
    1.36
    assing
    1.36
    idem
    1.36
    Activations Density 0.397%

    No Known Activations