© 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. 2-MLP-SM
    6. 26033
    Prev
    Next
    INDEX
    Explanations

    words related to clinical and economic assessments

    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
    273
    +0.13
    0.7%
    495
    +0.12
    0.7%
    116
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    248
    +0.13
    0.03
    433
    +0.12
    0.03
    495
    +0.10
    0.04
    Negative Logits
    £
    -3.49
    ı
    -3.38
    ĻĤ
    -3.38
    Īĺ
    -3.27
    ĥ
    -3.18
    Ĥ
    -3.14
    Į
    -3.13
    į
    -3.09
    Ī
    -3.07
    ľĵ
    -3.06
    POSITIVE LOGITS
    ration
    1.63
     aggravated
    1.59
     conform
    1.51
    ifications
    1.50
    gers
    1.44
    hest
    1.43
    arers
    1.43
     tires
    1.41
     "`
    1.38
    NOS
    1.38
    Activations Density 0.199%

    No Known Activations