© 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. 27161
    Prev
    Next
    INDEX
    Explanations

    the pronoun "this" 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
    432
    +0.12
    0.7%
    306
    +0.11
    0.6%
    331
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.12
    0.15
    26
    +0.11
    0.14
    199
    +0.11
    0.14
    Negative Logits
    ctica
    -1.66
    ¿½
    -1.64
     tamb
    -1.49
    )!
    -1.45
    GHz
    -1.44
    dale
    -1.39
     reference
    -1.37
     Transl
    -1.33
     attraction
    -1.33
    ?",
    -1.32
    POSITIVE LOGITS
    ulate
    1.45
    ults
    1.41
    irs
    1.40
    inous
    1.39
    won
    1.33
    gery
    1.32
    rift
    1.31
    ned
    1.31
     defeats
    1.30
    rade
    1.30
    Activations Density 0.274%

    No Known Activations