© 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. 11309
    Prev
    Next
    INDEX
    Explanations

    various products and accessories related to retail and fashion

    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
    48
    +0.15
    0.9%
    161
    +0.15
    0.8%
    17
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    44
    +0.15
    0.09
    129
    +0.15
    -0.04
    230
    +0.12
    0.02
    Negative Logits
    .]{}
    -1.89
    ]{.
    -1.77
    )]{}
    -1.74
    ément
    -1.72
    ↵Č
    -1.64
    `:
    -1.64
    ){#
    -1.60
     *[
    -1.59
    etically
    -1.57
    ```
    -1.55
    POSITIVE LOGITS
     Ratio
    1.69
     Suit
    1.65
     Shot
    1.61
    llo
    1.60
     Jail
    1.58
     Us
    1.56
     Version
    1.55
     Films
    1.54
     Mem
    1.52
     Profile
    1.52
    Activations Density 4.576%

    No Known Activations