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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27764
    Prev
    Next
    INDEX
    Explanations

    references to online discussion platforms and community interactions

    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
    376
    +0.14
    0.9%
    184
    +0.13
    0.8%
    96
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.14
    0.01
    264
    +0.13
    0.01
    96
    +0.09
    0.01
    Negative Logits
     normal
    -1.58
     sed
    -1.57
    ]>
    -1.52
     _________
    -1.52
     outgoing
    -1.52
     yours
    -1.51
     heart
    -1.51
     saline
    -1.43
     transgender
    -1.43
     dece
    -1.43
    POSITIVE LOGITS
    erne
    2.29
    helf
    2.21
    ière
    2.20
    erate
    2.04
    arium
    1.91
    ware
    1.85
    garten
    1.84
    ĻĤ
    1.82
    pieces
    1.81
    aji
    1.77
    Activations Density 0.006%

    No Known Activations