© 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 EvalsExportsinterp-engineNEWAPI 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. 23162
    Prev
    Next
    INDEX
    Explanations

    numerical values and their relationships in lists or sequences

    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
    156
    +0.17
    1.0%
    472
    +0.14
    0.8%
    171
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    171
    +0.17
    -0.01
    403
    +0.14
    0.06
    31
    +0.12
    0.09
    Negative Logits
    threat
    -1.40
     summit
    -1.31
    ¦
    -1.31
     minister
    -1.30
     overt
    -1.29
     diseng
    -1.27
     Authority
    -1.25
     conven
    -1.25
     revoked
    -1.25
    IRE
    -1.24
    POSITIVE LOGITS
    ?)
    1.80
    !)
    1.61
    ())
    1.61
    ])
    1.55
    ~)
    1.54
     onto
    1.54
    adays
    1.48
     alive
    1.48
    ')$
    1.47
    together
    1.43
    Activations Density 2.766%

    No Known Activations