© 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. 2-MLP-SM
    11. 24465
    Prev
    Next
    INDEX
    Explanations

    statements regarding abilities and characteristics, particularly in medical contexts

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    17
    +0.16
    0.9%
    337
    +0.13
    0.7%
    447
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    470
    +0.16
    0.10
    409
    +0.13
    0.09
    160
    +0.12
    0.09
    Negative Logits
     ours
    -1.77
     anyone
    -1.63
     theirs
    -1.58
    eness
    -1.55
     alike
    -1.52
    opic
    -1.51
     humans
    -1.50
     heart
    -1.50
    xture
    -1.50
     ]
    -1.47
    POSITIVE LOGITS
    Pub
    1.65
    ista
    1.56
    iop
    1.55
    icip
    1.54
    notes
    1.54
    illas
    1.52
    ias
    1.52
    κε
    1.50
     CIRCUIT
    1.49
    division
    1.48
    Activations Density 0.819%

    No Known Activations