© 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. Residuals
    9. 2-RES-SM
    11. 28622
    Prev
    Next
    INDEX
    Explanations

    references to films and the film industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-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_resid_post
    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
    93
    +0.16
    0.9%
    156
    +0.16
    0.9%
    100
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    93
    +0.16
    0.04
    100
    +0.16
    0.04
    502
    +0.14
    0.03
    Negative Logits
    ĥ½
    -2.46
    Ń
    -2.32
    ĭ
    -2.25
    ·
    -2.24
    ł
    -2.24
    Ĥ¬
    -2.18
    Į
    -2.16
    Ħ
    -2.12
    ĸ´
    -2.08
    «
    -2.08
    POSITIVE LOGITS
    iary
    1.94
     clips
    1.86
     footage
    1.85
    ic
    1.85
    ico
    1.79
    oon
    1.77
    fare
    1.77
    iller
    1.73
     theaters
    1.71
    iem
    1.69
    Activations Density 0.143%

    No Known Activations