Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27445
    Prev
    Next
    INDEX
    Explanations

    the pronoun "they" used in various contexts

    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
    169
    +0.13
    0.7%
    370
    +0.13
    0.7%
    473
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.13
    0.11
    352
    +0.13
    0.11
    143
    +0.12
    0.09
    Negative Logits
    olester
    -1.55
    enance
    -1.41
     bore
    -1.36
     member
    -1.36
    jcmm
    -1.33
    oker
    -1.33
    essel
    -1.30
    wide
    -1.29
    experienced
    -1.26
    mux
    -1.26
    POSITIVE LOGITS
    ories
    1.71
    ités
    1.51
     pronounce
    1.46
    ureus
    1.45
    arynge
    1.45
    orie
    1.44
    wash
    1.34
    uent
    1.29
    gett
    1.27
     conclusions
    1.25
    Activations Density 0.142%

    No Known Activations