© 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. 29353
    Prev
    Next
    INDEX
    Explanations

    repeated sequences of a specific character or string in the document

    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
    +0.12
    0.6%
    376
    +0.12
    0.6%
    192
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    133
    +0.12
    0.08
    17
    +0.12
    0.06
    482
    +0.10
    0.06
    Negative Logits
    ian
    -1.74
    iane
    -1.44
    reich
    -1.41
    eed
    -1.40
    olev
    -1.39
    ”),
    -1.38
     Correspond
    -1.37
     Prayer
    -1.35
     Speech
    -1.34
    ide
    -1.34
    POSITIVE LOGITS
    ĻĤ
    2.33
    Ģ
    2.08
    ľĵ
    1.99
    ł
    1.98
    ĨĴ
    1.95
    Ĥ¬
    1.90
    ij
    1.79
    Īĺ
    1.76
    ĥ
    1.76
    Ĺ
    1.74
    Activations Density 0.163%

    No Known Activations