© 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. 0-MLP-SM
    11. 29187
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical values or coded information

    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
    409
    +0.13
    0.7%
    269
    +0.13
    0.7%
    81
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.13
    0.02
    199
    +0.13
    0.02
    307
    +0.12
    0.02
    Negative Logits
    atitis
    -1.60
     pity
    -1.52
    aves
    -1.51
     least
    -1.48
    oles
    -1.47
     total
    -1.43
    amura
    -1.42
    olas
    -1.40
    '?
    -1.40
     contr
    -1.39
    POSITIVE LOGITS
    ¦
    2.52
    ®
    2.33
    ¥
    2.25
    Į
    2.24
    ģ
    2.21
    į
    2.17
    ³
    2.16
    ¶
    2.16
    ¯
    1.99
    Ĥ
    1.96
    Activations Density 0.014%

    No Known Activations