© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 27213
    Prev
    Next
    INDEX
    Explanations

    references to mechanical components, particularly hinges

    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
    142
    +0.16
    0.9%
    376
    +0.14
    0.8%
    470
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.01
    142
    +0.14
    0.01
    347
    +0.13
    0.01
    Negative Logits
    ¦
    -1.75
     shares
    -1.65
     only
    -1.51
     hosts
    -1.50
    ureus
    -1.48
     permission
    -1.47
    anner
    -1.42
    heres
    -1.39
     talented
    -1.34
     prospective
    -1.33
    POSITIVE LOGITS
    edly
    2.23
    eto
    1.81
    holes
    1.73
    etto
    1.67
    ulsions
    1.67
    ested
    1.61
    itives
    1.61
    hetto
    1.61
    eh
    1.59
    enum
    1.55
    Activations Density 0.022%

    No Known Activations