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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28206
    Prev
    Next
    INDEX
    Explanations

    references to personal pronouns and direct addresses

    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
    287
    +0.17
    1.0%
    341
    +0.14
    0.8%
    180
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    41
    +0.17
    0.18
    473
    +0.14
    0.17
    266
    +0.14
    0.16
    Negative Logits
    board
    -1.59
    \]](
    -1.55
    riors
    -1.45
    fare
    -1.45
    done
    -1.43
    walk
    -1.42
     worthwhile
    -1.40
    oe
    -1.38
     yours
    -1.36
     significantly
    -1.32
    POSITIVE LOGITS
    emann
    1.68
    idone
    1.57
    eman
    1.48
    eme
    1.36
     respectively
    1.33
     specification
    1.32
     elevation
    1.32
    ;|
    1.27
    Department
    1.26
    iment
    1.26
    Activations Density 0.463%

    No Known Activations